Feedback-based object detection for multi-person pose estimation

In this paper, a novel method is proposed for increasing the performance through coupling of top-down models adjusting the object detector based on a new loss function. Generally, object detectors and keypoint estimators are sequentially used in real-time multi-person pose estimations; however, these two models are separately trained. Therefore, the results of the object detector are not optimized for the keypoint estimator. To solve this problem, we analyze the relationship between the two models and propose a feedback-based loss optimization in the object detector, based on the estimation results of the keypoint estimator. In addition, the resulting bounding box of the object detector is readjusted to improve the accuracy of the keypoint estimation model. The experimental results demonstrate that the proposed approach can perform real-time operations with a high frame rate similar to that of the baseline model. Moreover, it achieved an accuracy of 74.2 average precision (AP), which is higher than the state-of-the-arts model including the human detector used in the experiment.     

基于GA-BP的汽车风振噪声声品质预测模型

目前对于汽车风振噪声的优化研究主要以声压级（Sound pressure level，SPL）作为单一评价指标，既不能全面反映噪声的物理属性，也无法考虑人耳对噪声的主观认知过程。为准确评价风振噪声，引入声品质，运用大涡模拟（Large eddy simulation，LES）对风振噪声进行数值仿真，根据实车道路试验判断仿真的准确性；对仿真结果进行声品质客观评价与主观评价，综合声品质客观评价参数与声品质主观评价试验结果建立BP神经网络预测模型；利用遗传算法（Genetic algorithm，GA），进一步对BP神经网络的结构参数进行优化，建立GA-BP声品质预测模型。研究结果表明，GA-BP声品质预测模型在训练速度和预测精度上都优于BP神经网络预测模型。预测模型基于声品质主客观评价结果，其预测值可以代替传统的声压级评价指标，为风振噪声提供更为准确合理的评价。     

致密砂岩油藏能量补充方式评价及优化

针对致密砂岩油藏大规模体积压裂开发后能量补充困难的问题,利用自主设计制作的大型人造三维岩心物理模型和物理模拟实验舱,开展致密砂岩油藏能量补充方式优化研究。实验结果表明:致密砂岩油藏压裂开发过程中,地层能量损耗严重,采取注水或注气的方式可有效进行能量补充;地层中裂缝规模越大,越有利于原油渗流,后续补充能量的传播范围越广,有助于进一步提高原油采收率;从提高驱油效率和扩大波及系数方面优选吞吐渗吸介质,CO₂均优于活性水,CO₂吞吐开发在矿场试验中取得了显著的增油效果,因此,CO₂吞吐作为一种有效的能量补充方式在致密油开发中展现了良好的应用前景。该文分析了致密砂岩储层水平井压裂开发的渗流规律,优选出致密砂岩储层大规模压裂开发后最佳渗吸介质,可为致密砂岩油藏开发设计提供重要的理论依据。     

钢混结构大型厂房整体式爆破拆除

采用整体式控制爆破拆除方案对华电扬州电厂钢筋混凝土框-排架结构厂房进行了爆破拆除。爆破前,对汽机房、厂房外墙和楼梯进行了预处理。将厂房划分为3个爆区,采用非电多回路网格式爆破网路,依靠东侧锅炉房倒塌施加在西侧锅炉房上的倾覆力矩,有效地克服了西侧锅炉房向西倒的难题,可为同类工程提供一定的参考。     

Convolutional Neural Network Auto Encoder Channel Estimation Algorithm in MIMO-OFDM System

Higher transmission rate is one of the technological features of prominently used wireless communication namely Multiple Input Multiple Output-Orthogonal Frequency Division Multiplexing (MIMO–OFDM). One among an effective solution for channel estimation in wireless communication system, specifically in different environments is Deep Learning (DL) method. This research greatly utilizes channel estimator on the basis of Convolutional Neural Network Auto Encoder (CNNAE) classifier for MIMO-OFDM systems. A CNNAE classifier is one among Deep Learning (DL) algorithm, in which video signal is fed as input by allotting significant learnable weights and biases in various aspects/objects for video signal and capable of differentiating from one another. Improved performances are achieved by using CNNAE based channel estimation, in which extension is done for channel selection as well as achieve enhanced performances numerically, when compared with conventional estimators in quite a lot of scenarios. Considering reduction in number of parameters involved and re-usability of weights, CNNAE based channel estimation is quite suitable and properly fits to the video signal. CNNAE classifier weights updation are done with minimized Signal to Noise Ratio (SNR), Bit Error Rate (BER) and Mean Square Error (MSE).     

Parameter characterization of HTPEMFC using numerical simulation and genetic algorithms

This paper develops a novel approach to the parameterisation of high temperature exchange membrane fuel cells (HTPEMFC) with limited and non-invasive measurements. The proposed method allows an effective identification of electrochemical parameters for three-dimensional fuel cell models by combining computational simulation tools and genetic algorithms. To avoid each evaluation undertaken by the optimisation method involving a complete computational simulation of the 3D model, a strategy has been designed that, thanks to an iterative process, makes it possible to decouple the fluid dynamic resolution from the electrochemistry one.Two electrochemical models have been incorporated into these tools to describe the behaviour of the catalyst layer, Butler-Volmer and spherical aggregate. For each one, a case study has been carried out to validate the results by comparing them with empirical data in the first model and with data generated by numerical simulation in the second. Results show that, from a set of measured operating conditions, it is possible to identify a unique set of electrochemical parameters that fits the 3D model to the target polarisation curve. The extension of this framework can be used to systematically estimate any model parameter in order to reduce the uncertainty in 3D simulation predictions.     

机器翻译译文质量估计综述

机器翻译译文质量估计(Quality Estimation,QE)是指在不需要人工参考译文的条件下,估计机器翻译系统产生的译文的质量,对机器翻译研究和应用具有很重要的价值。机器翻译译文质量估计经过最近几年的发展,取得了丰富的研究成果。该文首先介绍了机器翻译译文质量估计的背景与意义;然后详细介绍了句子级QE、单词级QE、文档级QE的具体任务目标、评价指标等内容,进一步概括了QE方法发展的三个阶段: 基于特征工程和机器学习的QE方法阶段,基于深度学习的QE方法阶段,融入预训练模型的QE方法阶段,并介绍了每一阶段中的代表性研究工作;最后分析了目前的研究现状及不足,并对未来QE方法的研究及发展方向进行了展望。     

建筑结构控制爆破拆除的力学分析与应用

应用运动学、动力学理论建立建(构)筑物控爆坍落过程的力学模型,进而研究在非定常约束条件下坍落结构的力学特征。首次提出了采用延时起爆技术时,非自由质点系及其广义坐标应是建立在每一段位上的瞬间虚位移。在此基础上,分析求解运动过程中时控单元的质点自由度,为精确选定爆破部位及时序提供了设计理论和计算依据。同时,结合振动理论,将控爆时差、结构载荷分布调制为振动系统,形成坍落结构梁板单元的强迫振动,充分实现在运动中进一步解体、破碎其自身结构,并形成具有明显缓冲效果的下落过程。应用实践结果证明力学分析是正确的,为工程结构爆破拆除计算机辅助设计及动态模拟技术的有效应用奠定了基础。