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。     

Machine fault diagnosis with small sample based on variational information constrained generative adversarial network

In actual engineering scenarios, limited fault data leads to insufficient model training and over-fitting, which negatively affects the diagnostic performance of intelligent diagnostic models. To solve the problem, this paper proposes a variational information constrained generative adversarial network (VICGAN) for effective machine fault diagnosis. Firstly, by incorporating the encoder into the discriminator to map the deep features, an improved generative adversarial network with stronger data synthesis capability is established. Secondly, to promote the stable training of the model and guarantee better convergence, a variational information constraint technique is utilized, which constrains the input signals and deep features of the discriminator using the information bottleneck method. In addition, a representation matching module is added to impose restrictions on the generator, avoiding the mode collapse problem and boosting the sample diversity. Two rolling bearing datasets are utilized to verify the effectiveness and stability of the presented network, which demonstrates that the presented network has an admirable ability in processing fault diagnosis with few samples, and performs better than state-of-the-art approaches.     

使能未来工厂的5G能力综述

5G系统将移动通信服务从移动电话、移动宽带和大规模机器通信扩展到新的应用领域，即所谓对通信服务有特殊要求的垂直领域。对使能未来工厂的5G能力进行了全面的分析总结，包括弹性网络架构、灵活频谱、超可靠低时延通信、时间敏感网络、安全和定位，而弹性网络架构又包括对网络切片、非公共网络、5G局域网和边缘计算的支持。希望从广度到深度，对相关的理论及技术应用做透彻、全面的梳理，对其挑战做清晰的总结，从而为相关研究和工程技术人员提供借鉴。     

基于全U网络的混凝土路面裂缝检测算法

针对现有的混凝土裂缝检测算法在各种复杂环境中检测精度不够、鲁棒性不强的问题,根据深度学习理论和U-net模型,提出一种全U型网络的裂缝检测算法。首先,依照原U-net模型路线构建网络;然后,在每个池化层后都进行一次上采样,恢复其在池化层之前的特征图规格,并将其与池化之前的卷积层进行融合,将融合之后的特征图作为新的融合层与原U-net网络上采样之后的网络层进行融合;最后,为了验证算法的有效性,在测试集中进行实验。结果表明,所提算法的平均精确率可达到83.48%,召回率为85.08%,F1为84.11%,相较于原U-net分别提升了1.48%,4.68%和3.29%,在复杂环境中也能提取完整裂缝,保证了裂缝检测的鲁棒性。     

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.     

Enhanced wide-activated residual network for efficient and accurate image deblocking

To save bandwidth and storage space as well as speed up data transmission, people usually perform lossy compression on images. Although the JPEG standard is a simple and effective compression method, it usually introduces various visually unpleasing artifacts, especially the notorious blocking artifacts. In recent years, deep convolutional neural networks (CNNs) have seen remarkable development in compression artifacts reduction. Despite the excellent performance, most deep CNNs suffer from heavy computation due to very deep and wide architectures. In this paper, we propose an enhanced wide-activated residual network (EWARN) for efficient and accurate image deblocking. Specifically, we propose an enhanced wide-activated residual block (EWARB) as basic construction module. Our EWARB gives rise to larger activation width, better use of interdependencies among channels, and more informative and discriminative non-linearity activation features without more parameters than residual block (RB) and wide-activated residual block (WARB). Furthermore, we introduce an overlapping patches extraction and combination (OPEC) strategy into our network in a full convolution way, leading to large receptive field, enforced compatibility among adjacent blocks, and efficient deblocking. Extensive experiments demonstrate that our EWARN outperforms several state-of-the-art methods quantitatively and qualitatively with relatively small model size and less running time, achieving a good trade-off between performance and complexity.     

建筑工业化发展的多群体演化博弈与仿真研究

新型建筑工业化具有高质量、低消耗、可循环发展等特征，其推广已上升到国家战略层面。利用演化博弈方法，建立“政府-开发商-银行” 的三方动态演化博弈模型，进行各博弈主体策略的演化稳定性分析，并针对初始状态、奖惩力度、借贷风险和开发成本等对演化结果的影响进行动态仿真。在此基础上， 考虑开发商群体的网络拓扑特征对演化真实性的影响，引入复杂网络理论， 以无标度网络为载体描述开发商个体的连接偏好和决策机制，构建政府监管下的建筑工业化扩散模型，并通过仿真深入研究相关因素对扩散深度的影响作用，最后结合仿真结果给出相应对策建议。     

Treatment of Brain Metastases of Non-Small Cell Lung Carcinoma

Lung cancer is one of the most common malignant neoplasms. As a result of the disease’s progression, patients may develop metastases to the central nervous system. The prognosis in this location is unfavorable; untreated metastatic lesions may lead to death within one to two months. Existing therapies—neurosurgery and radiation therapy—do not improve the prognosis for every patient. The discovery of Epidermal Growth Factor Receptor (EGFR)—activating mutations and Anaplastic Lymphoma Kinase (ALK) rearrangements in patients with non-small cell lung adenocarcinoma has allowed for the introduction of small-molecule tyrosine kinase inhibitors to the treatment of advanced-stage patients. The Epidermal Growth Factor Receptor (EGFR) is a transmembrane protein with tyrosine kinase-dependent activity. EGFR is present in membranes of all epithelial cells. In physiological conditions, it plays an important role in the process of cell growth and proliferation. Binding the ligand to the EGFR causes its dimerization and the activation of the intracellular signaling cascade. Signal transduction involves the activation of MAPK, AKT, and JNK, resulting in DNA synthesis and cell proliferation. In cancer cells, binding the ligand to the EGFR also leads to its dimerization and transduction of the signal to the cell interior. It has been demonstrated that activating mutations in the gene for EGFR-exon19 (deletion), L858R point mutation in exon 21, and mutation in exon 20 results in cancer cell proliferation. Continuous stimulation of the receptor inhibits apoptosis, stimulates invasion, intensifies angiogenesis, and facilitates the formation of distant metastases. As a consequence, the cancer progresses. These activating gene mutations for the EGFR are present in 10–20% of lung adenocarcinomas. Approximately 3–7% of patients with lung adenocarcinoma have the echinoderm microtubule-associated protein-like 4 (EML4)/ALK fusion gene. The fusion of the two genes EML4 and ALK results in a fusion gene that activates the intracellular signaling pathway, stimulates the proliferation of tumor cells, and inhibits apoptosis. A new group of drugs—small-molecule tyrosine kinase inhibitors—has been developed; the first generation includes gefitinib and erlotinib and the ALK inhibitor crizotinib. These drugs reversibly block the EGFR by stopping the signal transmission to the cell. The second-generation tyrosine kinase inhibitor (TKI) afatinib or ALK inhibitor alectinib block the receptor irreversibly. Clinical trials with TKI in patients with non-small cell lung adenocarcinoma with central nervous system (CNS) metastases have shown prolonged, progression-free survival, a high percentage of objective responses, and improved quality of life. Resistance to treatment with this group of drugs emerging during TKI therapy is the basis for the detection of resistance mutations. The T790M mutation, present in exon 20 of the EGFR gene, is detected in patients treated with first- and second-generation TKI and is overcome by Osimertinib, a third-generation TKI. The I117N resistance mutation in patients with the ALK mutation treated with alectinib is overcome by ceritinib. In this way, sequential therapy ensures the continuity of treatment. In patients with CNS metastases, attempts are made to simultaneously administer radiation therapy and tyrosine kinase inhibitors. Patients with lung adenocarcinoma with CNS metastases, without activating EGFR mutation and without ALK rearrangement, benefit from immunotherapy. This therapeutic option blocks the PD-1 receptor on the surface of T or B lymphocytes or PD-L1 located on cancer cells with an applicable antibody. Based on clinical trials, pembrolizumab and all antibodies are included in the treatment of non-small cell lung carcinoma with CNS metastases.