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。     

一种基于FCOS神经网络的小建筑物目标检测方法北大核心

提出了一种基于FCOS神经网络的小建筑物目标检测算法,针对FCOS模型在特征提取阶段提取到的小建筑物目标特征较少问题,引入多尺度检测和可变形卷积方式,加强网络对小建筑物目标的特征提取能力,并通过改进后的SGE注意力机制降低特征图中的干扰噪声权重。改进后的网络可以提取到更多的小建筑物目标特征,对环境干扰噪声的鲁棒性更强。在自己搭建的数据集上进行了实验测试,结果表明,在相同环境下网络改进后建筑物的整体检测准确率提升了1.7%,其中对小建筑物目标提升了3.6%,减少了小建筑物目标漏检、误检的问题。     

Optimal design and operation of integrated microgrids under intermittent renewable energy sources coupled with green hydrogen and demand scenarios

Renewable energy integration into existing or new energy hubs together with Green technologies such as Power to Gas and Green Hydrogen has become essential because of the aim of keeping the average global temperature rise within 2 ^°C with regard to the Paris Agreement. Hence, all energy markets are expected to face substantial transitions worldwide. On the other hand, investigation of renewable energy systems integrated with green chemical conversion, and in particular combination of green hydrogen and synthetic methanation, is still a scarce subject in the literature in terms of optimal and simultaneous design and operation for integrated energy grids under weather intermittency and demand uncertainty. In fact, the integration of such promising new technologies has been studied mainly in the operational phase, without considering design and management simultaneously. Thus, in this work, a multi-period mixed-integer linear programming (MILP) model is formulated to deal with the aforementioned challenges. Under current carbon dioxide limitations dictated by the Paris Agreement, this model computes the best configuration of the renewable and non-renewable-based generators, their optimal rated powers, capacities and scheduling sequences from a large candidate pool containing thirty-nine different equipment simultaneously. Moreover, the effect of the intermittent nature of renewable resources is analyzed comprehensively under three different scenarios for a specific location. Accordingly, a practical scenario generation method is proposed in this work. It is observed that photovoltaic, oil co-generator, reciprocating ICE, micro turbine, and bio-gasifier are the equipment that is commonly chosen under the three different scenarios. Results also show that concepts such as green hydrogen and power-to-gas are currently not preferable for the investigated location. On the other hand, analysis shows that if the emission limits are getting tightened, it is expected that constructing renewable resource-based grids will be economically more feasible.     

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).     

Stem Photosynthesis—A Key Element of Grass Pea (Lathyrus sativus L.) Acclimatisation to Salinity

Grass pea (Lathyrus sativus) is a leguminous plant of outstanding tolerance to abiotic stress. The aim of the presented study was to describe the mechanism of grass pea (Lathyrus sativus L.) photosynthetic apparatus acclimatisation strategies to salinity stress. The seedlings were cultivated in a hydroponic system in media containing various concentrations of NaCl (0, 50, and 100 mM), imitating none, moderate, and severe salinity, respectively, for three weeks. In order to characterise the function and structure of the photosynthetic apparatus, Chl a fluorescence, gas exchange measurements, proteome analysis, and Fourier-transform infrared spectroscopy (FT-IR) analysis were done inter alia. Significant differences in the response of the leaf and stem photosynthetic apparatus to severe salt stress were observed. Leaves became the place of harmful ion (Na⁺) accumulation, and the efficiency of their carboxylation decreased sharply. In turn, in stems, the reconstruction of the photosynthetic apparatus (antenna and photosystem complexes) activated alternative electron transport pathways, leading to effective ATP synthesis, which is required for the efficient translocation of Na⁺ to leaves. These changes enabled efficient stem carboxylation and made them the main source of assimilates. The observed changes indicate the high plasticity of grass pea photosynthetic apparatus, providing an effective mechanism of tolerance to salinity stress.     

基于条件信息卷积生成对抗网络的图像识别

传统的图像识别方法需要大量有标签样本进行训练，且模型训练难以达到稳定。针对这些问题，结合条件生成网络和信息最大化生成网络的结构优势建立了条件信息卷积生成网络（C-Info-DCGAN）。模型增加图像的类别信息和潜在信息作为输入数据，然后利用Q网络去更好地发挥类别信息和潜在信息对训练的引导作用，并且利用深度卷积网络来加强对图像特征的提取能力。实验结果表明，该方法能够加快模型训练收敛速度，并有效提高图像识别的准确率。     

An iterative approach for the discrete‐time dynamic control of Markov jump linear systems with partial information

The , and mixed dynamic output feedback control of Markov jump linear systems in a partial observation context is studied through an iterative approach. By partial information, we mean that neither the state variable x(k) nor the Markov chain θ(k) are available to the controller. Instead, we assume that the controller relies only on an output y(k) and a measured variable coming from a detector that provides the only information of the Markov chain θ(k). To solve the problem, we resort to an iterative method that starts with a state‐feedback controller and solves at each iteration a linear matrix inequality optimization problem. It is shown that this iterative algorithm yields to a nonincreasing sequence of upper bound costs so that it converges to a minimum value. The effectiveness of the iterative procedure is illustrated by means of two examples in which the conservatism between the upper bounds and actual costs is significantly reduced.     

Stability and stabilization for singularly perturbed systems with Markovian jumps

This article focuses on the stability and stabilization problems of singularly perturbed jump systems. Here, the singularly perturbed parameter (SPP) is also with Markov switching and satisfies any with positive bound predefined. First, stability conditions expressed ?_i‐free but involving its bound are developed by constructing an ?_i‐dependent Lyapunov function. Then, a method for state feedback stabilization controller depending on SPP is proposed, whose conditions are given in terms of linear matrix inequalities. Moreover, some special cases about deterministic SPP are considered too. Finally, two practical examples are used to demonstrate the effectiveness and superiorities of the proposed methods.     

矿用直线振动筛结构故障分析

针对煤矿选煤厂直线振动筛工作过程中出现的结构故障问题,采用有限元仿真与现场测试结合的方法对振动筛出现故障的原因进行了分析研究。介绍了振动筛的主要结构及常见故障,并以某矿选煤厂发生大梁断裂的振动筛为例,对该振动筛进行三维建模和有限元模态分析,分析结果表明:随着模态阶次的增加,振型的变化逐渐由移动转为结构本身的扭曲变形。在该振动筛空载工作状态下,选用本质安全型便携式测振记录仪进行振动测试并处理测试信号,得到该振动筛的工作频率。结合模态分析结果和实际测试结果,判断出空载时频繁运行振动筛是造成其大梁断裂的主要原因。根据故障原因给出维护建议:应当尽量避免振动筛在空载或物料较少的状态下长时间运行;在振动筛投入使用前,应预先了解振动筛的工作状态及可能存在的薄弱环节,尽可能避免结构故障,保证振动筛可靠运行。     

Mathematical formulation and heuristic algorithms for optimisation of auto-part milk-run logistics network considering forward and reverse flow of pallets

The operational planning of distribution network for automotive industry is complex with many conditions to consider, including heterogeneous fleet, enforcing the feasibility of 3D-packing of pallets into vehicles to address the vehicle's capacity in terms of weight and volume, compatibility of orders in a vehicle, returning empty pallets from assembly-plants backwards to suppliers, and delivery time windows. A mathematical model (MILP) is proposed that takes account of these conditions to minimise total transportation costs. The network structure can be a combination of direct shipment and milk-run for both forward and reverse flow of pallets. The model is solved optimally for small-size problems. For solving larger problems, a heuristic algorithm (in two versions) is proposed that uses a similarity measure to generate a reasonable list of orders. Best/first-fit strategies are employed to generate a feasible solution with the aid of a relaxed version of the proposed MILP. Improvement heuristics are also designed. Unlike most of existing constructive heuristics, our aim for developing the heuristic approach is to force routing decision, with all of its considerations, being made optimal. We also use the proposed best-fit strategy in the body of grouping evolution strategy (GES) algorithm to attain an effective meta-heuristic approach. The effectiveness of heuristics is tested on generated instances which demonstrates they are optimal for small-size problems. They are also tested on the data of daily auto-parts shipments gathered from the largest Iranian automobile company. Results demonstrate there exists a significant potential for cost saving through milk-run strategy compared with the direct shipping strategy.