Autonomous Parking-Lots Detection with Multi-Sensor Data Fusion Using Machine Deep Learning Techniques

The rapid development and progress in deep machine-learning techniques have become a key factor in solving the future challenges of humanity. Vision-based target detection and object classification have been improved due to the development of deep learning algorithms. Data fusion in autonomous driving is a fact and a prerequisite task of data preprocessing from multi-sensors that provide a precise, well-engineered, and complete detection of objects, scene or events. The target of the current study is to develop an in-vehicle information system to prevent or at least mitigate traffic issues related to parking detection and traffic congestion detection. In this study we examined to solve these problems described by (1) extracting region-of-interest in the images (2) vehicle detection based on instance segmentation, and (3) building deep learning model based on the key features obtained from input parking images. We build a deep machine learning algorithm that enables collecting real video-camera feeds from vision sensors and predicting free parking spaces. Image augmentation techniques were performed using edge detection, cropping, refined by rotating, thresholding, resizing, or color augment to predict the region of bounding boxes. A deep convolutional neural network F-MTCNN model is proposed that simultaneously capable for compiling, training, validating and testing on parking video frames through video-camera. The results of proposed model employing on publicly available PK-Lot parking dataset and the optimized model achieved a relatively higher accuracy 97.6% than previous reported methodologies. Moreover, this article presents mathematical and simulation results using state-of-the-art deep learning technologies for smart parking space detection. The results are verified using Python, TensorFlow, OpenCV computer simulation frameworks.     

O_2/Si(100)非重构表面LEPS相互作用势模型

对双原子分子O2与非重构Si（100）表面相互作用的LEPS半经验势模型进行了研究，其中表面作为具有波纹度的刚性表面进行处理。确立了系统的势能超曲面，得到的表面吸附特性与P．V．Smith等人基于ASED－MO方法的研究结果进行了定量对比分析。对不同入射条件下的分子－表面相互作用势也进行了研究。     

井结构参数对同井回灌地下水源热泵的影响

建立单一介质承压含水层中定流量同井回灌地下水源热泵地下水换热数学模型,并模拟分析含水层厚度、抽灌段滤管长度及其间距等井结构参数对同井回灌地下水源热泵地下水渗流和换热的影响。     

自振空化射流研究与应用进展

介绍一种新型射流——自振空化射流的设计原理、冲击压力特性、冲蚀破岩特性和现场应用情况。研究表明，以风琴管结构为基础设计的喷嘴可以产生强烈的自振空化射流，与锥角为 120°的普通锥形喷嘴相比，冲击压力脉动幅度和峰值分别提高24 ％和37 ％，冲蚀岩石效果提高1～2倍。自振空化射流已成功应用到石油工程中，研制出自振空化射流钻头、高压旋转自振空化射流处理近地层技术和自激波动注水技术，取得明显的经济效益。     

Neutrophils Mediate Pulmonary Artery Thrombosis In Situ

Pulmonary embolism is a life-threatening condition, which can result in respiratory insufficiency and death. Blood clots occluding branches of the pulmonary artery (PA) are traditionally considered to originate from thrombi in deep veins (usually in legs). However, growing evidence suggests that occlusion of the vessels in the lungs can develop without preceding deep vein thrombosis (DVT). In this work, we used an inferior vena cava (IVC) complete ligation model of DVT in Wistar rats to explore the possibility and mechanisms of PA thrombosis under the conditions where all routes of thrombotic mass migration from peripheral veins are blocked. We demonstrate that rats both with normal and reduced neutrophil counts developed thrombi in the IVC, although, neutropenia caused a substantial decrease in thrombus size and a shift from fresh fibrin toward mature fibrin and connective tissue inside the thrombus. Massive fibrin deposition was found in the PA branches in the majority of DVT rats with normal neutrophil counts, but in none of the neutropenic animals. Neutrophil ablation also abolished macroscopic signs of lung damage. Altogether, the results demonstrate that thrombi in the lung vasculature can form in situ by mechanisms that require local neutrophil recruitment taking place in the DVT setting.     

炼油厂深水井计算机集中监控系统的应用

针对炼油企业供水系统存在问题,阐述了炼油厂分散型水源井智能化集中监控的技术方案.对监控系统的硬件结构、程序设计、功能、技术特点和可靠性设计进行了较详细的介绍.     

基于深度学习的孔特征可制造性分析方法

针对传统基于知识库及规则库的零件可制造性分析方法柔性差,以及现有基于深度学习的可制造性分析方法无法给出零件具体不可制造原因的现状,提出一种基于深度学习的零件可制造性分析方法.首先,通过数字化建模技术构建大量带有具体可制造性类别标签的三维CAD模型,并进行点云提取,从而构建深度学习所需数据集;然后,基于PointNet网...     

有岩爆倾向深井矿山采矿巷道的失稳模式分析及其控制技术

冬瓜山铜矿深井具有高应力(30～38 MPa)、存在岩爆倾向的特点。根据原岩应力测量、岩石物理力学试验、岩体结构调查、数值模拟计算以及工程实际, 详细分析了处于各类岩体中的采矿巷道的失稳模式, 针对采矿巷道的岩体特性、工程部位及其作用以及预测破坏模式, 提出了不同的支护方式及参数, 取得了较好的效果。     

夹河矿深部煤巷围岩稳定性控制技术研究

为解决夹河矿深部开采时煤巷出现的围岩变形量大、支护体破坏严重等非线性大变形问题,采用现场工程调查、微观组构实验等手段,分析了巷道围岩破坏失稳主要是由于支护体与围岩在力学特性上的不耦合造成的。研究采用耦合支护非线性设计方法,得到锚网索耦合支护参数。现场试验表明,采用该设计方法进行锚网索耦合支护既能充分发挥锚网主动支护浅部围岩的能力,又能通过锚索调动深部围岩强度的支护能力,从而实现软岩巷道支护体与围岩在强度、刚度和结构上的耦合,发挥支护体与围岩共同承担荷载的作用,实现深部煤巷的稳定性．