基于度量学习的意图识别和槽填充方法

人机对话中小样本学习场景下的意图识别和槽填充,是自然语言处理的一个重要课题.本文采用基于度量学习的方法,通过计算query set中的样本与support set中样本的距离,寻找距离最近的类别样本作为分类标签,同时将两个任务联合进行训练,用以提升模型的效果.从实验结果中可以得出,本文提出的Fine-tune方法,对意图识别和槽填充任务都有一定的帮助和提升.胶囊网络在意图识别中也起到了一定的效果,可以帮助去除一部分无关信息,但对槽填充任务的帮助不明显;而任务自适应的投影网络,可以更好地将不同类的向量分开,提升了两个任务的性能.     

Reconstructing gene regulatory networks with a memetic-neural hybrid based on fuzzy cognitive maps

Reconstructing gene regulatory networks (GRNs) plays an important role in identifying the complicated regulatory relationships, uncovering regulatory patterns in cells, and gaining a systematic view for biological processes. In order to reconstruct large-scale GRNs accurately, in this paper, we first use fuzzy cognitive maps (FCMs), which are a kind of cognition fuzzy influence graphs based on fuzzy logic and neural networks, to model GRNs. Then, a novel hybrid method is proposed to reconstruct GRNs from time series expression profiles using memetic algorithm (MA) combined with neural network (NN), which is labeled as MANN_FCM-GRN. In MANN_FCM-GRN, the MA is used to determine regulatory connections in GRNs and the NN is used to determine the interaction strength of the regulatory connections. In the experiments, the performance of MANN_FCM-GRN is validated on both synthetic data and the benchmark dataset DREAM3 and DREAM4. The experimental results demonstrate the efficacy of MANN_FCM-GRN and show that MANN_FCM-GRN can reconstruct GRNs with high accuracy without expert knowledge. The comparison with existing algorithms also shows that MANN_FCM-GRN outperforms ant colony optimization, non-linear Hebbian learning, and real-coded genetic algorithms.

     

急性炎性疾病患者乳酸林格氏液液体动力学

目的:探索炎性疾病患者的乳酸林格氏液（Ringer's lactate,RL）液体动力学特征以及炎性生物标记物是否可以作为协变量影响RL分布和排泄。方法:本研究为前瞻性队列研究。选择40例美国麻醉医师分级（ASA）I-II级，腹腔镜下择期胆囊切除术（胆囊炎组，n=20）或者腹腔镜下急诊阑尾切除术（阑尾炎组，n=20）。所有患者麻醉诱导前开始输注RL，按15 mL/kg，35 min内输毕。采用酶联免疫（enzyme-linked immunosorbent assay,ELISA）方法测定血浆炎症（TNF-α,IL-10和CRP）或者内皮损伤生物标记物（syndecan-1,SDC-1）；利用血红蛋白（Hb）稀释-时间曲线和尿量，使用Phoenix软件，采用非线性混合效应模型分析计算RL液体动力学参数和协变量的影响。结果:与胆囊炎组相比，阑尾炎组RL从组织间隙到血浆的转运速率常数（k21）显著降低（14×10-3min-1 versus 35×10-3min-1;P=0.012）。阑尾炎组C反应蛋白（CRP）升高［中位数38.1(1.8-143.6) μg/mL versus 1.3(0.1-159.0) μg/mL;P<0.001］；与清醒状态相比，麻醉期间（输液开始后30～45 min），液体从中央室中到外周室的转运速率常数（k12）显著增加（57×10-3min-1 versus 32×10-3min-1；P<0.01）。清除速率常数（k10）降低90%（0.6×10-3min-1 versus 5.3×10-3min-1;P<0.001）。无论在清醒状态还是麻醉状态下低血压均能降低液体清除；炎症或者内膜损伤的生物标记物不能作为显著影响RL液体动力学参数的协变量。结论:阑尾炎或者胆囊炎患者术前输入液体后“炎症反应的生物标记物”不是RL的液体动力学的协变量，但是两组患者中，全身麻醉期间输入液体的清除率下降。     

烟道流量计量标准装置

为了解决我国烟道流量计的量值溯源问题,中国计量科学研究院建立了烟道流量计量标准装置。装置使用可溯源至标准转盘的激光多普勒测速仪作为原级标准器,采用激光多普勒流速剖面扫描和超声流量计波动修正的方式测量标准流量,经校准的8声道超声流量计为工作级标准表,具备了908~104840m3/h的测量能力,扩展不确定度为0.62%(k=2),可对最大口径为1m的流量计进行校准。装置下游测试段包括圆形管段和矩形管段,能够开展烟道流量计测量性能的研究。     

Low complexity quantum private queries protocol

Private information retrieval(PIR) is an important privacy protection issue of secure multi-party computation, but the PIR protocols based on classical cryptography are vulnerable because of new technologies,such as quantum computing and cloud computing. The quantum private queries(QPQ) protocols available, however, has a high complexity and is inefficient in the face of large database. This paper, based on the QKD technology which is mature now, proposes a novel QPQ protocol utilizing the key dilution and auxiliary parameter. Only N quits are required to be sent in the quantum channel to generate the raw key, then the straight k bits in the raw key are added bitwise to dilute the raw key, and a final key is consequently obtained to encrypt the database. By flexible adjusting of auxiliary parameters θ and k, privacy is secured and the query success ratio is improved. Feasibility and performance analyses indicate that the protocol has a high success ratio in first-trial query and is easy to implement, and that the communication complexity of O(N) is achieved.     

应用膨胀算法提取目标的直接定位算法

为了解决被动雷达系统中的多发射源定位问题，提出了一种基于多重信号分类(MUSIC)算法和图像膨胀(IE)算法的直接定位方法。该方法结合了谱分析中的MUSIC思想，通过对接收量测协方差矩阵进行特征分析求解目标的位置。首先，在目标个数未知的前提下，利用Akaike信息准则(AIC)来确定模型阶数；然后，推导了基于MUSIC的定位代价函数；之后，利用图像膨胀算法处理得到的代价函数平面；最后，膨胀处理后的输出为目标个数及目标位置的估计值。提出的算法有效地解决了目标检测及提取的问题，能够确定多个目标的位置坐标，为后续的定位性能分析提供可能性，也保证了算法的完整性。进一步地分析了多个临近目标情况下影响目标提取性能的主要因素。     

Visual Detection of Adenosine Triphosphate by Taylor Rising: A Simple Point-of-Care Testing Method Based on Rolling Circle Amplification

Rapid and sensitive point-of-care testing (POCT) is an extremely critical mission in practical applications, especially for rigorous military medicine, home health care, and in the third world. Here, we report a visual POCT method for adenosine triphosphate (ATP) detection based on Taylor rising in the corner of quadratic geometries between two rod surfaces. We discuss the principle of Taylor rising, demonstrating that it is significantly influenced by contact angle, surface tension, and density of the sample, which are controlled by ATP-dependent rolling circle amplification (RCA). In the presence of ATP, RCA reaction effectively suppresses Taylor-rising behavior, due to the increased contact angle, density, and decreased surface tension. Without addition of ATP, untriggered RCA reaction is favorable for Taylor rising, resulting in a significant height. With this proposed method, visual sensitive detection of ATP without the aid of other instruments is realized with only a 5 μL droplet, which has good selectivity and a low detection limit (17 nM). Importantly, this visual method provides a promising POCT tool for user-friendly molecular diagnostics.