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。     

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。     

胶带斜井在冶金矿山深井开拓中的应用探讨

针对某在建矿山深井开拓方案探索需求，通过对胶带运输系统发展应用情况介绍和胶带运输系统运输特性影响因素分析，并结合深井开拓胶带斜井方案与竖井加胶带斜井方案投资经济性比较，以及对胶带运输系统在运行过程中关键问题的分析和讨论，得出随着胶带运输技术的不断发展，在大规模深井开拓中，胶带斜井开拓将大有可为，为冶金矿山深井开拓方案选择提供决策支持。     

基于深度信念网络的列车故障音频诊断方法

铁路在交通运输行业有着举足轻重的地位，一旦列车发生故障将会导致严重的生命财产损失。由于列车发生故障的概率相对较低，因此难以捕获列车的故障样本。针对上述问题，提出了一种无监督学习的列车故障识别方法，通过检测列车音频信号来识别列车故障。该方法基于深度信念网络(DBN)，利用小波包分解提取检测信号的特征向量并将其作为DBN的输入，待网络充分训练后，由训练好的DBN识别当前列车的运行状况。现场监测实验结果表明，该方法能够在无监督的条件下有效识别列车故障，保障了列车的运行安全。     

基于深度学习的秀丽隐杆线虫显微图像分割方法

利用计算机实现自动、准确的秀丽隐杆线虫(C.elegans)的各项形态学参数分析,至关重要的是从显微图像上分割出线虫体态,但由于显微镜下的图像噪声较多,线虫边缘像素与周围环境相似,而且线虫的体态具有鞭毛和其他附着物需要分离,多方面因素导致设计一个鲁棒性的C.elegans分割算法仍然面临着挑战。针对这些问题,提出了一种基于深度学习的线虫分割方法,通过训练掩模区域卷积神经网络(Mask R-CNN)学习线虫形态特征实现自动分割。首先,通过改进多级特征池化将高级语义特征与低级边缘特征融合,结合大幅度软最大损失(LMSL)损失算法改进损失计算;然后,改进非极大值抑制;最后,引入全连接融合分支等方法对分割结果进行进一步优化。实验结果表明,相比原始的Mask R-CNN,该方法平均精确率(AP)提升了4.3个百分点,平均交并比(mIOU)提升了4个百分点。表明所提出的深度学习分割方法能够有效提高分割准确率,在显微图像中更加精确地分割出线虫体。     

Modeling the effect of deep traps on the capacitance–voltage characteristics of p-type Si-doped GaAs Schottky diodes grown on high index GaAs substrates

Numerical simulation, using SILVACO-TCAD, is carried out to explain experimentally observed effects of different types of deep levels on the capacitance–voltage characteristics of p-type Si-doped GaAs Schottky diodes grown on high index GaAs substrates. Two diodes were grown on (311)A and (211)A oriented GaAs substrates using Molecular Beam Epitaxy (MBE). Although, deep levels were observed in both structures, the measured capacitance–voltage characteristics show a negative differential capacitance (NDC) for the (311)A diodes, while the (211)A devices display a usual behaviour. The NDC is related to the nature and spatial distribution of the deep levels, which are characterized by the Deep Level Transient Spectroscopy (DLTS) technique. In the (311)A structure only majority deep levels (hole traps) were observed while both majority and minority deep levels were present in the (211)A diodes. The simulation, which calculates the capacitance–voltage characteristics in the absence and presence of different types of deep levels, agrees well with the experimentally observed behaviour.     

改进HSR-FCN的服装图像识别分类算法研究

目前网络上的服装图像数量增长迅猛，对于大量服装图像实现智能分类的需求日益增加。将基于区域的全卷积网络（Region-Based Fully Convolutional Networks，R-FCN）引入到服装图像识别中，针对服装图像分类中网络训练时间长、形变服装图像识别率低的问题，提出一种新颖的改进框架HSR-FCN。新框架将R-FCN中的区域建议网络和HyperNet网络相融合，改变图片特征学习方式，使得HSR-FCN可以在更短的训练时间内达到更高的准确率。在模型中引入了空间转换网络，对输入服装图像和特征图进行了空间变换及对齐，加强了对多角度服装和形变服装的特征学习。实验结果表明，改进后的HSR-FCN模型有效地加强了对形变服装图像的学习，且在训练时间更短的情况下，比原来的网络模型R-FCN平均准确率提高了大约3个百分点，达到96.69%。     

When Does Communication Learning Need Hierarchical Multi-Agent Deep Reinforcement Learning

Abstract

Multi-agent systems need to communicate to coordinate a shared task. We show that a recurrent neural network (RNN) can learn a communication protocol for coordination, even if the actions to coordinate are performed steps after the communication phase. We show that a separation of tasks with different temporal scale is necessary for successful learning. We contribute a hierarchical deep reinforcement learning model for multi-agent systems that separates the communication and coordination task from the action picking through a hierarchical policy. We further on show, that a separation of concerns in communication is beneficial but not necessary. As a testbed, we propose the Dungeon Lever Game and we extend the Differentiable Inter-Agent Learning (DIAL) framework. We present and compare results from different model variations on the Dungeon Lever Game.     

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.