基于PCAU-Net的快速多通道磁共振成像方法

多通道磁共振成像方法采用多个接收线圈同时欠采样k空间以加快成像速度,并基于后处理算法重建图像,但在较高加速因子时,其图像重建质量仍然较差．本文提出了一种基于PCAU-Net的快速多通道磁共振成像方法,将单通道实数U型卷积神经网络拓展到多通道复数卷积神经网络,设计了一种结构不对称的U型网络结构,通过在解码部分减小网络规模以降低模型的复杂度．PCAU-Net网络在跳跃连接前增加了1×1卷积,以实现跨通道信息交互．输入和输出之间利用残差连接为误差的反向传播提供捷径．实验结果表明,使用规则和随机采样模板,在不同加速因子时,相比常规的GRAPPA重建算法和SPIRiT重建方法,本文提出的PCAU-Net方法可高质量重建出磁共振复数图像,并且相比于PCU-Net方法,PCAU-Net减少了模型参数、缩短了训练时间．     

Enhancing network lifespan in wireless sensor networks using deep learning based Graph Neural Network

Inadequate energy of sensors is one of the most significant challenges in the development of a reliable wireless sensor network (WSN) that can withstand the demands of growing WSN applications. Implementing a sleep-wake scheduling scheme while assigning data collection and sensing chores to a dominant group of awake sensors while all other nodes are in a sleep state seems to be a potential way for preserving the energy of these sensor nodes. When the starting energy of the nodes changes from one node to another, this issue becomes more difficult to solve. The notion of a dominant set-in graph has been used in a variety of situations. The search for the smallest dominant set in a big graph might be time-consuming. Specifically, we address two issues: first, identifying the smallest possible dominant set, and second, extending the network lifespan by saving the energy of the sensors. To overcome the first problem, we design and develop a deep learning-based Graph Neural Network (DL-GNN). The GNN training method and back-propagation approach were used to train a GNN consisting of three networks such as transition network, bias network, and output network, to determine the minimal dominant set in the created graph. As a second step, we proposed a hybrid fixed-variant search (HFVS) method that considers minimal dominant sets as input and improves overall network lifespan by swapping nodes of minimal dominating sets. We prepared simulated networks with various network configurations and modeled different WSNs as undirected graphs. To get better convergence, the different values of state vector dimensions of the input vectors are investigated. When the state vector dimension is 3 or 4, minimum dominant set is recognized with high accuracy. The paper also presents comparative analyses between the proposed HFVS algorithm and other existing algorithms for extending network lifespan and discusses the trade-offs that exist between them. Lifespan of wireless sensor network, which is based on the dominant set method, is greatly increased by the techniques we have proposed.     

Delay optimization and energy balancing algorithm for improving network lifetime in fixed wireless sensor networks

Since wireless in terms of energy-restricted processes, dispersion radii, processing power limitations, buffers, bandwidth-limited connections, active network topologies, and network stream of traffic outlines, sensor networks provide difficult design issues. The number of hops and latency are decreased if there is a relay mote because it interacts directly with relay motes that are closer to the destination mote. The tremendous intensive research in the area of Wireless Sensor Networks (WSN) has gained a lot of significance among the technical community and research. The job of WSN is to sense the data using sensor motes, pass on the data to the destination detection mote which is associated with a processing center and can be used in multiple spans of Internet of Things (IoT) applications. Wireless sensor network has a set of sensor motes. By making use of sensor mote placement strategy all the sensor motes are spread in an area with each mote having its own exceptional location. Internet of things applications are delay sensitive those applications have a challenge of forming the complete path at a lower delay constraint. The proposal is to modify the game theory energy balancing algorithm by making use of relay motes so that overall network lifetime is increased. It has been proved that modified GTEB is better with respect to existing algorithms in terms of delay, figure of hops, energy depletion, figure of alive motes, figure of dead motes, lifespan ratio, routing overhead and throughput.     

Adaptive multimode transmission in wireless sensor networks with energy harvesting

Limited energy has always been an important factor restricting the development of wireless sensor networks. The unbalanced energy consumption of nodes will accelerate the death of some nodes. To solve the above problems, an adaptive routing algorithm for energy collection sensor networks based on distributed energy saving clustering (DEEC) is proposed. In each hop of data transmission, the optimal mode is adaptively selected from four transmission modes: single-hop cooperative, multi-hop cooperative, single-hop non-cooperative and multi-hop non-cooperative, so as to reduce and balance the energy consumption of nodes. The performance of the proposed adaptive multi-mode transmission method and several benchmark schemes are evaluated and compared by computer simulation, where a few performance metrics such as the network lifetime and throughput are adopted. The results show that, the proposed method can effectively reduce the energy consumption of the network and prolong the network lifetime; it is superior to various benchmark schemes.     

Unsupervised LoS/NLoS identification in mmWave communication using two-stage machine learning framework

Identification of line-of-sight (LoS)/ non-LoS (NLoS) condition in millimeter wave (mmWave) communication is important for localization and unobstructed transmission between a base station (BS) and a user. A sudden obstruction in a link between a BS and a user can result in poorly received signal strength or termination of communication. Channel features obtained by the estimation of channel state information (CSI) of a user at the BS can be used for identifying LoS/NLoS condition. With the assumption of labeled CSI, existing machine learning (ML) methods have achieved satisfactory performance for LoS/NLoS identification. However, in a real communication environment, labeled CSI is not available. In this paper, we propose a two-stage unsupervised ML based LoS/NLoS identification framework to address the lack of labeled data. We conduct experiments for the outdoor scenario by generating data from the NYUSIM simulator. We compare the performance of our method with the supervised deep neural network (SDNN) in terms of accuracy and receiver characteristic curves. The proposed framework can achieve an accuracy of 87.4% and it outperforms SDNN. Further, we compare the performance of our method with other state-of-the-art LoS/NLoS identification schemes in terms of accuracy, recall, precision, and F1-score.     

基于麻雀搜索算法结合深度前馈神经网络的近红外模型转移方法研究

该文提出了一种基于麻雀搜索算法结合深度前馈神经网络（SSA－DFN）的近红外光谱模型转移方法。使用深度前馈神经网络拟合不同仪器采集到的光谱之间的非线性函数映射,并将麻雀搜索算法用于网络各层连接权值和阈值的初始化,通过种群中个体位置的迭代更新,求得连接权值和阈值的最优初始值;通过多次调整深度前馈神经网络模型的超参数,使网络拟合效果趋于最优,最终确定转移函数。为验证方法的有效性,分别从烟叶近红外光谱谱图、主成分投影和预测结果的角度,将SSA－DFN方法与分段直接校正算法（PDS）、典型相关性分析算法（CCA）转移前后的效果进行了对比。结果表明SSA－DFN方法转移后的从机光谱与原主机光谱重合度最高,转移后主、从机总糖、烟碱含量的预测结果差异不显著,预测平均误差从8.32%、9.15%分别降至4.65%、4.82%,预测均方根误差（RMSEP）和决定系数（R2）等指标均优于PDS和CCA,取得了最佳的转移效果,可满足企业需求。结果表明该方法是一种有效的模型转移方法。     

Morphology controllable conjugated network polymers based on AIE-active building block for TNP detection

Luminescent conjugated network polymer is one of the most promising chemo-sensors owing to their good chemical/optical stability and multiple functionalization.Herein,three conjugated network polymers were prepared by using aggregation-induced emission active 1,1,2,2-tetrakis(4-formyl-(1,1'-biphenyl))-ethane(TFBE) unit as monomer and hydrazine as linker.Through regulating the synthetical condition,the polyme ric network can form either unifo rm two-dimensional azine-linked nanosheets(ANS),conjugated microporous polymers(A-CMP) or covalent organic frameworks(A-COF).All of these polymers exhibited good stability and high fluorescence quantum efficiency with the quantum yield of6.31% for A-NS,5.26% for A-CMP,and 5.80% for A-COF,as well as fast and selective fluorescence quenching response to 2,4,6-trinitrophenol(TNP).And the best TNP sensing performance with the Stern-Volmer constants(K_(sv)) values up to 8 × 10~5 L/mol and a detection limit of 0.09 μmol/L was obtained for A-NS.The study explores various strategies to construct conjugated polymers with different nanoarchitectures based on the same building block for sensitive detection of explosives.     

丹荷颗粒治疗高脂血症质量标志物发现研究

为寻找丹荷颗粒治疗高脂血症的质量标志物,该研究基于丹荷颗粒体内成分分析结果,采用Cytoscape软件构建高脂血症-共有靶点-丹荷颗粒体内成分作用网络,利用DAVID及String数据库分别对共有靶点进行生物过程、通路富集及网络拓扑分析,明确丹荷颗粒降脂作用关键靶点及成分,再建立油酸诱导的HepG2细胞脂质堆积模型验证关键成分的降脂药效,最后结合相关成分在制剂中的含量、稳定性、特征性综合确定质量标志物。结果发现,丹荷颗粒体内成分作用于CES1、ADORA2A、ADORA1、APOB、LDLR、PPARA、PPARG、INSR、ESR2、ESR1共10个高脂血症疾病靶点,主要参与脂质代谢过程以及PPAR、cAMP信号通路,其中LDLR、PPARA、PPARG可能是关键靶点,而网络中与关键靶点直接作用的成分为白藜芦醇、柚皮素。白藜芦醇和柚皮素均可降低油酸诱导的HepG2细胞内脂滴数量,改善细胞脂质堆积严重程度,并显著降低细胞内甘油三酯含量,可能为关键成分;鉴于入体成分白藜芦醇和柚皮素来源于制剂中虎杖苷及柚皮苷,且制剂中虎杖苷及柚皮苷特征明显、含量丰富、稳定,故虎杖苷及柚皮苷可作为丹荷颗粒治疗高脂血症的质量标志物。该研究为丹荷颗粒质量标准的建立提供了合理的候选质控指标。     

基于内源性致香物质和化学计量学的烟草感官评价研究

采用主成分分析法结合遗传算法和神经网络,建立了基于烟草内源性致香物质的感官质量评价预测模型。利用气相色谱-质谱(GC-MS)技术对超临界萃取-分子蒸馏所得烟草精油中的内源性致香组分进行定性定量分析,汇总各类致香指标后,对其进行主成分分析;以提取所得5个主成分的得分作为输入变量,感官评吸分数作为输出变量,分别使用标准BP神经网络和遗传算法(GA)优化的BP神经网络建立预测模型。对比实验结果表明,GA优化后的模型预测效果更优,其预测值与实验值间的相关系数为0.96,预测均方根误差为1.81,说明GA-BP模型具有更好的拟合能力和预测能力,该模型能有效地预测烟草精油的感官品质。     

结冷胶与聚乙二醇丙烯酸酯双网络凝胶的制备及生物相容性评价

针对结冷胶脆性较大的问题,将聚乙二醇丙烯酸酯(PEGDA)引入结冷胶,通过紫外交联制备了结冷胶/PEGDA双网络凝胶,并对单组分凝胶和双网络凝胶的溶胀性能、微观形貌、拉伸力学性能、动态压缩性能和流变性能等进行比较.结果表明,双网络凝胶在类生理环境中具有较小的溶胀率和较好的尺寸稳定性,PEGDA的引入能够大幅度提高结冷胶的韧性,双网络凝胶的拉断伸长率可达340%,断裂能达1.01×103J/m2,与天然关节软骨相当.将成纤维细胞种植在凝胶内部进行体外三维立体培养,结果显示,细胞在凝胶内部生存状态良好,双网络凝胶的细胞负载率高于单网络结冷胶,说明该体系在生物医用领域具有良好的应用前景.