基于改进MobileFaceNet的人脸识别方法北大核心

针对目前大多数人脸识别算法参数多、计算量大,难以部署到移动端和嵌入式设备中的问题,提出了一种基于改进MobileFaceNet的人脸识别方法。通过对MobileFaceNet模型结构的调整,将bottleneck模块优化为sandglass模块,改良深度卷积和逐点卷积的相对位置,适当增大sandglass模块的输出通道数,从而减少特征压缩时的信息丢失,增强人脸空间特征的提取。实验结果表明:改进后的方法在LFW测试数据集上准确率达99.15%,模型大小和计算量分别仅为原算法的61%和45%,验证了所提方法的有效性。     

爆破位置对深凹露天矿山炮烟扩散的影响研究

深凹露天矿山由于其特殊的结构,爆破产生的炮烟扩散稀释较为困难,严重危害生产作业人员的生命安全与健康。基于实际矿山构建了深凹露天矿山的二维物理及数学模型,采用非稳态数值分析方法研究了不同爆破位置下,深凹露天矿山采坑内爆破炮烟的扩散规律。研究结果表明：不同爆破位置下,露天采坑内均出现复环流,爆破点位置是影响露天采坑内风流结构特征的重要因素；露天采坑内的炮烟最高浓度均随着时间变化而逐渐下降,但下降的速率逐步减小,呈现三个阶段的下降趋势；爆破位置位于背风侧时露天采坑内的炮烟最高浓度和降至安全浓度所需时间远高于迎风侧三个爆破位置；随着背风侧爆破点距采坑底部距离的减小,炮烟最高浓度及降至安全浓度所需时间先降低后增加,炮烟最高浓度及降至安全浓度所需时间随着迎风侧爆破位置距采坑底部距离的减小而增加。研究结果对于指导深凹露天矿山企业合理组织爆破后的生产作业和保障作业人员安全具有重要意义。     

MHD mixed convection of a Cu–water nanofluid flow through a channel with an open trapezoidal cavity and an elliptical obstacle

In the current work, numerical simulations are achieved to study the properties and the characteristics of fluid flow and heat transfer of (Cu–water) nanofluid under the magnetohydrodynamic effects in a horizontal rectangular canal with an open trapezoidal enclosure and an elliptical obstacle. The cavity lower wall is grooved and represents the heat source while the obstacle represents a stationary cold wall. On the other hand, the rest of the walls are considered adiabatic. The governing equations for this investigation are formulated, nondimensionalized, and then solved by Galerkin finite element approach. The numerical findings were examined across a wide range of Richardson number (0.1 ≤ Ri ≤ 10), Reynolds number (1 ≤ Re ≤ 125), Hartmann number (0 ≤ Ha ≤ 100), and volume fraction of nanofluid (0 ≤ φ ≤ 0.05). The current study's findings demonstrate that the flow strength increases inversely as the Reynolds number rises, which pushes the isotherms down to the lower part of the trapezoidal cavity. The Nu_avg rises as the Ri rise, the maximum Nu_avg = 10.345 at Ri = 10, Re = 50, ϕ = 0.05, and Ha = 0; however, it reduces with increasing Hartmann number. Also, it increase by increasing ϕ, at Ri = 10, the Nu_avg increased by 8.44% when the volume fraction of nanofluid increased from (ϕ = 0–0.05).     

基于卷积神经网络的5G蜂窝网络无线定位方法

5G蜂窝网络发展迅猛，其覆盖面积将逐渐增大，因此使用5G蜂窝网络进行定位是有研究潜力的研究方向。本文提出一种新的深度学习技术来实现高效、高精度和低占用的定位，以代替传统指纹定位过程中繁重的指纹库生成以及距离计算。该方法建立了一个特殊的卷积神经网络，并根据5G天线信号的接收信号强度指示、相位和到达角等特征量，选择合适的输入数据格式构造样本组建训练集，对该卷积神经网络进行训练。训练得到的卷积神经网络可以替代指纹定位中的庞大指纹库，非常有利于直接在5G移动设备端实现定位。虽然卷积神经网络在训练过程中需要大量时间，但在训练完毕后直接进行分类定位的速度非常快，可以保障定位实现的实时性。本文所实现的卷积神经网络权重与偏置所占内存不到0.5 MB，且能够在实际应用环境中以95%的定位准确率以及0.1 m的平均定位精度实现高精度定位。     

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。     

基于FLAC3D的破碎围岩巷道支护效果分析

为了解破碎围岩分别采用锚杆支护、锚喷支护以及锚喷+锚索耦合三种支护方式下的支护效果,进而为破碎围岩巷道选择合理的支护方式提供参考。通过借助FLAC^3D软件建立数值模型,分析不同支护条件下的破碎围岩巷道位移量、应力分布以及塑性区的时空演化特征。结果表明,采用锚喷+锚索耦合支护时,可以较好的控制巷道围岩的位移量、减小应力集中效应、缩小塑性区的影响范围。     

Method for calculating horizontal drain induced non-linear and large strain degree of consolidation

Consolidating dredged clay slurries using a combination of vacuum pressure and prefabricated horizontal drains (PHDs) is widely used in practice. This is a large strain problem, but there is no existing large strain theory for PHD induced consolidation. A method with explicit equations has been proposed to consider both mechanical and geometrical non-linearities in analyzing PHD induced consolidation. The method considers stepwise variation of properties using imaginary time concept. An imaginary time is determined by the condition of continuity of degree of consolidation before and after changing the properties. Then the method was applied to analyze a large scale model test of vacuum consolidation with PHD. Two analyses were conducted. One considered both the mechanical and geometrical non-linearity (large strain), and another only considered mechanical non-linearity (small strain). The results of large strain analysis agree with the measured settlement curve and excess pore pressures well. While the small strain analysis under-estimated the rate of consolidation significantly. The results from this study indicate that for analyzing PHD induced consolidation of clay slurries considering the effect of large strain is important, and the proposed method can be a useful design tool.     

Adaptive investigation of the optical properties of polymer fibers from mixing noisy phase shifting microinterferograms using deep learning algorithms

In this article, an adaptive denoising method is suggested to accurate investigate the optical and structural features of polymeric fibers from noisy phase shifting microinterferograms. The mixed class of noise that may produce in the phase-shifting interferometric techniques is established. To our knowledge, this is an early study considered the mixing noises that may occur in microinterferograms. The suggested method utilized the convolution neural networks to detect the noise class and then denoising, it according to its class. Four convolution neural networks (Googlenet, VGG-19, Alexnet, and Alexnet–SVM) are refined to perform the automatic classification process for the noise class in the established data set. The network with the highest validation and testing accuracy of these networks is considered to apply the suggested method on realistic noisy microinterferograms for polymeric fibers, polypropylene and antimicrobial polyethylene terephthalate)/titanium dioxide, recoded using interference microscope. Also, the suggested method is applied on noisy microinterferograms include crazing and nanocomposite material. The demodulated phase maps and the three-dimensional birefringence profiles are calculated for tested fibers according to the suggested method. The obtained results are compared with the published data for these fibers and found to be in good agreements.     

Deep Learning Based Process Analytics Model for Predicting Type 2 Diabetes Mellitus

Process analytics is one of the popular research domains that advanced in the recent years. Process analytics encompasses identification, monitoring, and improvement of the processes through knowledge extraction from historical data. The evolution of Artificial Intelligence (AI)-enabled Electronic Health Records (EHRs) revolutionized the medical practice. Type 2 Diabetes Mellitus (T2DM) is a syndrome characterized by the lack of insulin secretion. If not diagnosed and managed at early stages, it may produce severe outcomes and at times, death too. Chronic Kidney Disease (CKD) and Coronary Heart Disease (CHD) are the most common, long-term and life-threatening diseases caused by T2DM. Therefore, it becomes inevitable to predict the risks of CKD and CHD in T2DM patients. The current research article presents automated Deep Learning (DL)-based Deep Neural Network (DNN) with Adagrad Optimization Algorithm i.e., DNN-AGOA model to predict CKD and CHD risks in T2DM patients. The paper proposes a risk prediction model for T2DM patients who may develop CKD or CHD. This model helps in alarming both T2DM patients and clinicians in advance. At first, the proposed DNN-AGOA model performs data preprocessing to improve the quality of data and make it compatible for further processing. Besides, a Deep Neural Network (DNN) is employed for feature extraction, after which sigmoid function is used for classification. Further, Adagrad optimizer is applied to improve the performance of DNN model. For experimental validation, benchmark medical datasets were used and the results were validated under several dimensions. The proposed model achieved a maximum precision of 93.99%, recall of 94.63%, specificity of 73.34%, accuracy of 92.58%, and F-score of 94.22%. The results attained through experimentation established that the proposed DNN-AGOA model has good prediction capability over other methods.     

Acquisition and Spread of Antimicrobial Resistance: A tet(X) Case Study

Understanding the mechanisms leading to the rise and dissemination of antimicrobial resistance (AMR) is crucially important for the preservation of power of antimicrobials and controlling infectious diseases. Measures to monitor and detect AMR, however, have been significantly delayed and introduced much later after the beginning of industrial production and consumption of antimicrobials. However, monitoring and detection of AMR is largely focused on bacterial pathogens, thus missing multiple key events which take place before the emergence and spread of AMR among the pathogens. In this regard, careful analysis of AMR development towards recently introduced antimicrobials may serve as a valuable example for the better understanding of mechanisms driving AMR evolution. Here, the example of evolution of tet(X), which confers resistance to the next-generation tetracyclines, is summarised and discussed. Initial mechanisms of resistance to these antimicrobials among pathogens were mostly via chromosomal mutations leading to the overexpression of efflux pumps. High-level resistance was achieved only after the acquisition of flavin-dependent monooxygenase-encoding genes from the environmental microbiota. These genes confer resistance to all tetracyclines, including the next-generation tetracyclines, and thus were termed tet(X). ISCR2 and IS26, as well as a variety of conjugative and mobilizable plasmids of different incompatibility groups, played an essential role in the acquisition of tet(X) genes from natural reservoirs and in further dissemination among bacterial commensals and pathogens. This process, which took place within the last decade, demonstrates how rapidly AMR evolution may progress, taking away some drugs of last resort from our arsenal.