基于推理注意力机制的二阶段网络图像修复

现有的图像修复方法在处理大面积缺失或高度纹理化的图像时，通常会产生扭曲的结构或与周围区域不一致的模糊纹理，无法重建合理的图像结构。为此，提出了一种基于推理注意力机制的二阶段网络图像修复方法。首先通过边缘生成网络生成合理的幻觉边缘信息，然后在图像补全网络完成图像的重建工作。为了进一步生成视觉效果更逼真的图像，提高图像修复的精确度，在图像补全网络采用推理注意力机制，有效控制了生成特征的不一致性，从而生成更有效的信息。所提方法在多个数据集上进行了实验验证，结果表明该图像修复方法的结构相似性指数达到了88.9%，峰值信噪比达到了25.56 dB，与现有的图像修复方法相比，该方法具有更高的图像修复精确度，生成的图像更逼真。     

Learn decision trees with deep visual primitives

In this paper, we strive to propose a self-interpretable framework, termed PrimitiveTree, that incorporates deep visual primitives condensed from deep features with a conventional decision tree, bridging the gap between deep features extracted from deep neural networks (DNNs) and trees’ transparent decision-making processes. Specifically, we utilize a codebook, which embeds the continuous deep features into a finite discrete space (deep visual primitives) to distill the most common semantic information. The decision tree adopts the spatial location information and the mapped primitives to present the decision-making process of the deep features in a tree hierarchy. Moreover, the trained interpretable PrimitiveTree can inversely explain the constituents of the deep features, highlighting the most critical and semantic-rich image patches attributing to the final predictions of the given DNN. Extensive experiments and visualization results validate the effectiveness and interpretability of our method.     

计算机网络办公自动化及安全策略探究

互联网通讯采取标准化模式主要以TCP/IP协议为载体,通讯的优越特性体现在同时具备便捷性与开放性,为办公提供很大的便利,但基于网络系统也会入侵病毒、也会给信息数据与办公体系安全性造成威胁,直接影响企业综合稳定发展。据此,为保障办公工作的顺利开展,本文对计算机网络办公自动化及安全策略进行详细分析。     

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.     

建筑工业化发展的多群体演化博弈与仿真研究

新型建筑工业化具有高质量、低消耗、可循环发展等特征，其推广已上升到国家战略层面。利用演化博弈方法，建立“政府-开发商-银行” 的三方动态演化博弈模型，进行各博弈主体策略的演化稳定性分析，并针对初始状态、奖惩力度、借贷风险和开发成本等对演化结果的影响进行动态仿真。在此基础上， 考虑开发商群体的网络拓扑特征对演化真实性的影响，引入复杂网络理论， 以无标度网络为载体描述开发商个体的连接偏好和决策机制，构建政府监管下的建筑工业化扩散模型，并通过仿真深入研究相关因素对扩散深度的影响作用，最后结合仿真结果给出相应对策建议。     

Public perceptions on artificial intelligence driven disaster management: Evidence from Sydney,Melbourne and Brisbane

In recent years, artificial intelligence (AI) is being increasingly utilised in disaster management activities. The public is engaged with AI in various ways in these activities. For instance, crowdsourcing applications developed for disaster management to handle the tasks of collecting data through social media platforms, and increasing disaster awareness through serious gaming applications. Nonetheless, there are limited empirical investigations and understanding on public perceptions concerning AI for disaster management. Bridging this knowledge gap is the justification for this paper. The methodological approach adopted involved: Initially, collecting data through an online survey from residents (n = 605) of three major Australian cities; Then, analysis of the data using statistical modelling. The analysis results revealed that: (a) Younger generations have a greater appreciation of opportunities created by AI-driven applications for disaster management; (b) People with tertiary education have a greater understanding of the benefits of AI in managing the pre- and post-disaster phases, and; (c) Public sector administrative and safety workers, who play a vital role in managing disasters, place a greater value on the contributions by AI in disaster management. The study advocates relevant authorities to consider public perceptions in their efforts in integrating AI in disaster management.     

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。     

Total Site Hydrogen Integration with fresh hydrogen of multiple quality and waste hydrogen recovery in refineries

This paper proposes a novel method combining Pinch Methodology and waste hydrogen recovery, aiming to minimise fresh hydrogen consumption and waste hydrogen discharge. The method of multiple-level resource Pinch Analysis is extended to the level of Total Site Hydrogen Integration by considering fresh hydrogen sources with various quality. Waste hydrogen after Total Site Integration is further regenerated. The technical feasibility and economy of the various purification approaches are considered, demonstrated with a case study of a refinery hydrogen network in a petrochemical industrial park. The results showed that fresh hydrogen usage and waste hydrogen discharge could be reduced by 21.3% and 67.6%. The hydrogen recovery ratio is 95.2%. It has significant economic benefits and a short payback period for Total Site Hydrogen Integration with waste hydrogen purification. The proposed method facilitates the reuse of waste hydrogen before the purification process that incurs an additional environmental footprint. In line with the Circular Economy principles, hydrogen resource is retained in the system as long as possible before discharge.     

Generating Questions Based on Semi-Automated and End-to-End Neural Network

With the emergence of large-scale knowledge base, how to use triple information to generate natural questions is a key technology in question answering systems. The traditional way of generating questions require a lot of manual intervention and produce lots of noise. To solve these problems, we propose a joint model based on semi-automated model and End-to-End neural network to automatically generate questions. The semi-automated model can generate question templates and real questions combining the knowledge base and center graph. The End-to-End neural network directly sends the knowledge base and real questions to BiLSTM network. Meanwhile, the attention mechanism is utilized in the decoding layer, which makes the triples and generated questions more relevant. Finally, the experimental results on SimpleQuestions demonstrate the effectiveness of the proposed approach.