INDIANA: An interactive system for assisting database exploration

We propose INDIANA, a system conceived to support a novel paradigm of database exploration. INDIANA assists the users who are interested in gaining insights about a database though an interactive and incremental process, like a conversation that does not happen in natural language. During this process, the system iteratively provides the user with some features of the data that might be “interesting” from the statistical viewpoint, receiving some feedbacks that are later used by the system to refine the features provided to the user in the next step. A key ability of INDIANA is to assist “data enthusiastic” users (i.e., inexperienced or casual users) in the exploration of transactional databases in an interactive way. For this purpose, we develop a number of novel, statistically-grounded algorithms to support the interactive exploration of the database. We report an in-depth experimental evaluation to show that the proposed system guarantees a very good trade-off between accuracy and scalability, and a user study that supports the claim that the system is effective in real-world database-exploration tasks.     

胶东三山岛西岭金矿区NW向断裂带的确定：综合物探证据

三山岛西岭金矿区位于渤海之滨，与北部海域金矿区相互连接，形成金资源量近千吨的巨型金矿床，矿床为地下与海底开采。区域内断裂发育，分布有NE向和NW向断裂，其中NE向断裂为控矿构造，而NW向断裂多具有不同程度的导水性，对矿床安全开采影响重大。基于矿区地质条件与地球物理特征，采用高精度磁测法和音频大地电磁（AMT）法在矿区东部进行了勘查试验，根据显示的磁性异常与电性异常，在平面上解译了NW向断裂(F-1、F-2)与NE向断裂（F-3、F-4），在L1剖面上解译了4条断裂，在L2剖面上解译了3条断裂。综合判断解译信息，NW向F-1断裂在平面与剖面上都反映良好。同时，与北部海域NW向构造研究资料进行对比分析，结果显示西岭矿区F-1推断断层与北部海域B-F4断层特征一致，吻合较好，推断西岭矿区NW向F-2断裂被F-3断裂错断。研究结果说明综合物探方法在该区域可行有效，为下一步钻孔验证NW向断裂存在，判断断裂富水及导水性质，以及未来矿床开发利用提供了地球物理依据。     

Model-Based Design Space Exploration for FPGA-based Image Processing Applications Employing Parameterizable Approximations

The increasing demand for low power consumption and high computational performance is outpacing available technological improvements in embedded systems. Approximate computing is a novel design paradigm trying to bridge this gap by leveraging the inherent error resilience of certain applications and trading in quality to achieve reductions in resource usage. Numerous approximation methods have emerged in this research field. While these methods are commonly demonstrated in isolation, their combination can increase the achieved benefits in complex systems. However, the propagation of errors throughout the system necessitates a global optimization of parameters, leading to an exponentially growing design space. Additionally, the parameterization of approximated components must consider potential cross-dependencies between them. This work proposes a systematic approach to integrate and optimally configure parameterizable approximate components in FPGA-based applications, focusing on low-level but high-bandwidth image processing pipelines. The design space is explored by a multi-objective genetic algorithm which takes parameter dependencies between different components into account. During the exploration, appropriate models are used to estimate the quality-resource trade-off for probed solutions without the need for time-consuming synthesis. We demonstrate and evaluate the effectiveness of our approach on two image processing applications that employ multiple approximations. The experimental results show that the proposed methods are able to produce a wide range of Pareto-optimal solutions, offering various choices regarding the desired quality-resource trade-off.     

含煤盆地深层“超饱和”煤层气形成条件

中国深层煤层气资源丰富，但总体勘探和认识程度较低，尚未形成较为系统的深层煤层气地质理论。通过解剖分析准噶尔盆地白家海凸起和鄂尔多斯盆地临兴区块深层"超饱和"煤层气井的试气/生产动态，估算原地游离气的含气量，分析了深层"超饱和"煤层气的形成条件。研究表明：①深层"超饱和"煤层气储层中除吸附气外，还含有原地游离气，用常规试气方法可直接获得气流，煤层气的产出不明显依赖于排水降压；②埋藏超过一定深度，在煤阶和温度的综合作用下，煤的吸附能力将随埋深的继续增加而降低，煤层中吸附气的饱和度有增加的趋势，在达到吸附饱和后，出现原地游离气并形成"超饱和"煤层气，盆地深层具有"超饱和"煤层气形成的优势条件；③由于地温梯度和压力梯度的不同，不同盆地"超饱和"煤层气出现的临界深度不同，异常高压和异常高热流可以降低深层"超饱和"煤层气形成的临界深度；④深层"超饱和"煤层气开发具有大大缩短见气时间、充分利用地层能量和累积产水量低等优势，有望成为未来煤层气勘探开发的一个重要领域。     

基于深度学习的人体姿态估计方法综述

基于深度学习的人体姿态估计方法旨在通过构建合适的神经网络，直接从二维的图像特征中回归出人体姿态信息。主要按照2D人体姿态估计到3D人体姿态估计的顺序，并从单人检测与多人检测、稀疏的关节点检测与密集的模型构建等方面，对近年来基于深度学习的人体姿态估计方法进行系统介绍，从而初步了解如何通过深度学习的方法得到人体姿态的各个要素，包括肢体部件的相对朝向和比例尺度、骨骼关节点的位置坐标和连接关系，甚至更为复杂的人体蒙皮模型信息。最后,对当前研究面临的挑战以及未来的热点动向进行概述，清晰地呈现出该领域的发展脉络。     

基于深度学习的视频跟踪研究进展综述

近年来深度学习迅猛发展，颠覆了语音识别、图像分类、文本理解等领域的算法设计思路。深度学习因其具备强大的特征提取能力，在图像识别领域的成绩尤为突出。然而深度学习与视频监控领域的结合并不多，由于深度模型具有多层网络结构，算法复杂度大，训练和更新模型时比较耗时，很难满足实时性要求。回顾了深度学习的发展史，介绍了最近10年来国内外深度学习主要模型，论述了基于深度学习的目标跟踪算法，指出了各算法的优缺点，最后对当前该领域存在的问题和发展前景进行了总结和展望。     

流量替代渗透率评价破碎性储层工作流体伤害程度

若地层岩石整体强度偏低,在力学环境改变后岩石易破碎成不规则破裂体,则储存油气资源的此类破碎地层被称为破碎性储层。由于破碎性储层在纵向上存在着较强的非均质性,通过测试单个柱塞岩样在工作流体伤害前后的渗透率变化难以体现工作流体对储层的整体伤害程度。为此,利用达西定律先从理论上探讨用流量替代渗透率定量表征储层伤害程度的可行性,再开展单层开采、双层及三层并采的流量测试实验,评价工作流体对单层、多层储层的整体伤害程度,并将流量损害率与渗透率损害率进行对比以求证流量替代渗透率的可行性。研究结果表明:①单层开采时,流量损害率与渗透率损害率基本一致,渗透率损害率是流量损害率的一种特殊形式;②双层及三层并采时,单层各自稳定流量损害率与渗透率损害率接近,且流量损害率可以定量表征并采储层的整体伤害程度,而渗透率损害率则无法定量表证;③稳定流量损害率较累积流量损害率更接近渗透率损害率。结论认为,测定稳定流量可以替代测定渗透率评价工作流体对破碎性储层的伤害程度,从而为优选工程技术与评价工作流体的适应性提供了方法依据。     

基于深度残差学习的自动驾驶道路场景理解

随着道路场景理解技术的快速发展，自主驾驶领域取得了长足的进步。在相关任务中，包括道路分割、分类和车辆检测的实时性和准确性是安全性的一个关键问题。为此，提出了一个具有编/解码器网络结构的基于深度残差学习的方法。一方面，编码器网络结构使用不同层次的残差网络来提取高维中的抽象特征，这些特征在接下来的三个任务中共享使用；另一方面，解码器网络结构采用一种子任务的并行计算机制，即道路分割、车辆检测和道路分类任务同时执行。此外，全卷积神经网络用于对提取的图像特征进行上采样以解决道路分割问题。最终，实验结果表明在保证高精度的前提下处理帧率可达到15 fps以上。     

Dual closed-loops current controller for a 4-leg shunt APF based on repetitive control

ABSTRACT

Current repetitive control strategy for a 4-leg APF is usually of a poor speed in responding to the drastic changes in load harmonic profile. In this paper, a dual closed-loop current controller composed of a repetitive control-based outer loop and a PI-based inner loop is proposed to improve the performance of a 4-leg APF, with a focus on response speed and harmonic current compensation gain. The principle of the dual loop controller is explained in detail, and the stability of the system is analysed thoroughly. To further decrease the inherent time delay associated with the PWM strategy, a zero-sequence-voltage-based PWM strategy is proposed to solve the complexity in the implementation of 3D-SVPWM methods. By formulating the relationship between the duty ratio of the neutral leg control pulse and the zero-sequence-component of the reference voltages, the duty ratios of the other three legs can be calculated conveniently. The simulation and lab experiment results are provided to verify the correctness and effectiveness of the proposed dual closed-loop current controller and the zero-sequence-voltage-based PWM strategy.     

基于改进卷积神经网络的单幅图像超分辨率重建方法

对于重建图像存在的边缘失真和纹理细节信息模糊的问题，提出一种基于改进卷积神经网络（CNN）的图像超分辨率重建方法。首先在底层特征提取层以三种插值方法和五种锐化方法进行多种预处理操作，并将只进行一次插值操作的图像和先进行一次插值后进行一次锐化的图像合并排列成三维矩阵；然后在非线性映射层将预处理后构成的三维特征映射作为深层残差网络的多通道输入，以获取更深层次的纹理细节信息；最后在重建层为减少图像重建时间在网络结构中引入亚像素卷积来完成图像重建操作。在多个常用数据集上的实验结果表明，与经典方法相比，所提方法重建图像的纹理细节信息和高频信息能得到更好的恢复，峰值信噪比（PSNR）平均增加0.23 dB，结构相似性（SSIM）平均增加0.0066。在保证图像重建时间的前提下，所提方法更好地保持重建图像的纹理细节并减少图像边缘失真，提升重建图像的性能。