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。     

疫情下电磁场理论课程的网络教学

本文主要总结了新冠疫情期间作者的电磁场理论课程在线教学经验。对比分析了录播和直播的优缺点后,选择录播教学方式。基于超星网络教学平台,展示了录播网络教学的具体措施,包括网上答疑和学习效果检查以及在线批改作业等。给出了网络教学可以为线下教学继续使用的方法和手段,为疫情结束后的正常教学提供了新的网络教学补充措施。     

5G核心网业务模型的智能化预测研究

摘 要：核心网业务模型的建立是5G网络容量规划和网络建设的基础，通过现有方法得到的理论业务模型是静态不可变的且与实际网络存在偏离。为了克服现有5G核心网业务模型与现网模型适配性较差以及规划设备无法满足用户实际业务需求的问题，提出了一种长短期记忆（long short-term memory，LSTM）网络与卷积LSTM （convolution LSTM，ConvLSTM）网络双通道融合的 5G 核心网业务模型预测方法。该方法基于人工智能（artificial intelligence，AI）技术以实现高质量的核心网业务模型的智能预测，形成数据反馈闭环，实现网络自优化调整，助力网络智能化建设。     

Learn decision trees with deep visual primitives

In this paper, we strive to propose a self-interpretable framework, termed PrimitiveTree, that incorporates deep visual primitives condensed from deep features with a conventional decision tree, bridging the gap between deep features extracted from deep neural networks (DNNs) and trees’ transparent decision-making processes. Specifically, we utilize a codebook, which embeds the continuous deep features into a finite discrete space (deep visual primitives) to distill the most common semantic information. The decision tree adopts the spatial location information and the mapped primitives to present the decision-making process of the deep features in a tree hierarchy. Moreover, the trained interpretable PrimitiveTree can inversely explain the constituents of the deep features, highlighting the most critical and semantic-rich image patches attributing to the final predictions of the given DNN. Extensive experiments and visualization results validate the effectiveness and interpretability of our method.     

基于RGB颜色信息聚类的光谱反射率重建

针对光谱反射率研究中因训练样本数据量大造成的冗杂等问题，提出了一种基于RGB信息进行聚类的样本分类方法。首先对颜色进行聚类并确定聚类个数，后对每一类光谱反射率使用BP神经网络分别进行重建。对于实验结果，使用ΔE₀₀、均方根误差（RMSE）以及适应度系数等标准进行评价，同时与主成分分析算法进行对比。从实验分析可得出，在聚类数目为7时光谱反射率重建效果最好，这时的平均CIE2000的色差为0.836，平均RMSE为0.0149，平均适应度系数为99.82%，并且，在最后对重建色差较大的色块进行了优化处理。实验证明，颜色聚类方法可以很好的应用于光谱反射率重建。     

国际橄榄理事会的定位和使命及相关标准（网络首发、推荐阅读）

The International Olive Council(IOC) is an international intergovernmental organization dedicated to olive oil and table olives, aiming at modernizing olive production, coordinating olive policies, improving the regulation of international trade, defending the quality of the olive sector and promoting olive oil and table olives to increase their consumption. The IOC grants recognition of laboratories and tasting panels in annual trials when they meet the conditions given in the decisions adopting the IOC certificate for laboratories for the physico–chemical testing of olive oil and laboratories for the sensory analysis of virgin olive oils. The IOC establishes analysis methods applying to olive oils and olive pomace oils for purity, quality and organoleptic assessment. The IOC elaborates guides of storage conditions for olive oils and olive pomace oils, of managing virgin olive oil tasting panels and of sensory testing laboratories. In future works, the IOC includes activities to identify analytical criteria for detecting fraud and guaranteeing the quality of olive oils and olive pomace oils.     

Techno-economic feasibility assessment of sorption enhanced gasification of municipal solid waste for hydrogen production

Waste-to-fuel coupled with carbon capture and storage is forecasted to be an effective way to mitigate the greenhouse gas emissions, reduce the waste sent to landfill and, simultaneously, reduce the dependence of fossil fuels. This study evaluated the techno-economic feasibility of sorption enhanced gasification, which involves in-situ CO₂ capture, and benchmarked it with the conventional steam gasification of municipal solid waste for H₂ production. The impact of a gate fee and tax levied on the fossil CO₂ emissions in economic feasibility was assessed. The results showed that the hydrogen production was enhanced in sorption enhanced gasification, that achieved an optimum H₂ production efficiency of 48.7% (T = 650 °C and SBR = 1.8). This was 1.0% points higher than that of the conventional steam gasification (T = 900 °C and SBR = 1.2). However, the total efficiency, which accounts for H₂ production and net power output, for sorption enhanced gasification was estimated to be 49.3% (T = 650 °C and SBR = 1.8). This was 4.4% points lower than the figure estimated for the conventional gasification (T = 900 °C and SBR = 1.2). The economic performance assessment showed that the sorption enhanced gasification will result in a significantly higher levelised cost of hydrogen (5.0 €/kg) compared to that estimated for conventional steam gasification (2.7 €/kg). The levelised cost of hydrogen can be reduced to 4.5 €/kg on an introduction of the gate fee of 40.0 €/t_MSW. The cost of CO₂ avoided was estimated to be 114.9 €/tCO₂ (no gate fee and tax levied). However, this value can be reduced to 90.1 €/tCO₂ with the introduction of an emission allowance price of 39.6 €/tCO₂. Despite better environmental performance, the capital cost of sorption enhanced gasification needs to be reduced for this technology to become competitive with mature gasification technologies.     

Optimization and regularization of complex task decomposition for blind removal of multi-factor degradation

Most existing image restoration methods based on deep neural networks are developed for images which only degraded by a single degradation mode and imaging under an ideal condition. They cannot be directly used to restore the images degraded by multi-factor coupling. A complex task decomposition regularization optimization strategy (TDROS) is proposed to solve the problem. The restoration of images degraded by multi-factor coupling is a complex task that can be solved by separating these multiple factors, that is, breaking the complex task into numbers of simpler tasks to make the entire complex problem be overcome more easily. Motivated by this idea, the TDROS decomposes the complex task of image restoration into two sub-task: the potential task constrained by regularization and the main task for reconstructing high-definition images. In TDROS, the front of the neural network is focused on the restoration of images degraded by additive noise, while the other part of the network is focused mainly on the restoration of images degraded by blur. We applied the TDROS to an 11-layer convolutional neural network (CNN) and compared it with initial CNNs from the aspects of restoration accuracy and generalization ability. Based on these results, we used TDROS to design a novel network model for the restoration of atmospheric turbulence-degraded images. The experimental results demonstrate that the proposed TDROS can improve the generalization ability of the existing network more effectively than current popular methods, offering a better solution for the problem of severely degraded image restoration. Moreover, the TDROS concept provides a flexible framework for low-level visual complex tasks and can be easily incorporated into existing CNNs.     

Mutual information maximizing GAN inversion for real face with identity preservation

Recent generative adversarial networks (GANs) have yielded remarkable performance in face image synthesis. GAN inversion embeds an image into the latent space of a pretrained generator, enabling it to be used for real face manipulation. However, current inversion approaches for real faces suffer the dilemma of initialization collapse and identity loss. In this paper, we propose a hierarchical GAN inversion for real faces with identity preservation based on mutual information maximization. We first use a facial domain guaranteed initialization to avoid the initialization collapse. Furthermore, we prove that maximizing the mutual information between inverted faces and their identities is equivalent to minimizing the distance between identity features from inverted and original faces. Optimization for real face inversion with identity preservation is implemented on this mutual information-maximizing constraint. Extensive experimental results show that our approach outperforms state-of-the-art solutions for inverting and editing real faces, particularly in terms of face identity preservation.