基于多通道的ICU脑血管疾病死亡风险预测模型

死亡风险预测指根据病人临床体征监测数据来预测未来一段时间的死亡风险。对于ICU病患，通过死亡风险预测可以有针对性地对病人做出临床诊断，以及合理安排有限的医疗资源。基于临床使用的MEWS和Glasgow昏迷评分量表，针对ICU病人临床监测的17项生理参数，提出一种基于多通道的ICU脑血管疾病死亡风险预测模型。引入多通道概念应用于BiLSTM模型，用于突出每个生理参数对死亡风险预测的作用。采用Attention机制用于提高模型预测精度。实验数据来自MIMIC [Ⅲ]数据库，从中提取3?080位脑血管疾病患者的16?260条记录用于此次研究，除了六组超参数实验之外，将所提模型与LSTM、Multichannel-BiLSTM、逻辑回归（logistic regression）和支持向量机（support vector machine, SVM）四种模型进行了对比分析，准确率Accuracy、灵敏度Sensitive、特异性Specificity、AUC-ROC和AUC-PRC作为评价指标，实验结果表明，所提模型性能优于其他模型，AUC值达到94.3%。     

A self-adaptive synthetic over-sampling technique for imbalanced classification

Traditionally, in supervised machine learning, (a significant) part of the available data (usually 50%-80%) is used for training and the rest—for validation. In many problems, however, the data are highly imbalanced in regard to different classes or does not have good coverage of the feasible data space which, in turn, creates problems in validation and usage phase. In this paper, we propose a technique for synthesizing feasible and likely data to help balance the classes as well as to boost the performance in terms of confusion matrix as well as overall. The idea, in a nutshell, is to synthesize data samples in close vicinity to the actual data samples specifically for the less represented (minority) classes. This has also implications to the so-called fairness of machine learning. In this paper, we propose a specific method for synthesizing data in a way to balance the classes and boost the performance, especially of the minority classes. It is generic and can be applied to different base algorithms, for example, support vector machines, k-nearest neighbour classifiers deep neural, rule-based classifiers, decision trees, and so forth. The results demonstrated that (a) a significantly more balanced (and fair) classification results can be achieved and (b) that the overall performance as well as the performance per class measured by confusion matrix can be boosted. In addition, this approach can be very valuable for the cases when the number of actual available labelled data is small which itself is one of the problems of the contemporary machine learning.     

Recent Biophysical Issues About the Preparation of Solute-Filled Lipid Vesicles

Here we report some recent biophysical issues on the preparation of solute-filled lipid vesicles and their relevance to the construction of “synthetic cells.” First, we introduce the “semi-synthetic minimal cells” as the liposome-based cell-like systems, which contain a minimal number of biomolecules required to display simple and complex biological functions. Next, we focus on recent aspects related to the construction of synthetic cells. Emphasis is given to the interplay between the methods of synthetic cell preparation and the physics of solute encapsulation. We briefly introduce the notion of structural and compositional “diversity” in synthetic cell populations.     

面部运动单元检测研究综述

面部运动单元检测旨在让计算机从给定的人脸图像或视频中自动检测需要关注的运动单元目标。经过二十多年的研究，尤其是近年来越来越多的面部运动单元数据库的建立和深度学习的兴起，面部运动单元检测技术发展迅速。首先，阐述了面部运动单元的基本概念，介绍了已有的常用面部运动单元检测数据库，概括了包括预处理、特征提取、分类器学习等步骤在内的传统检测方法；然后针对区域学习、面部运动单元关联学习、弱监督学习等几个关键研究方向进行了系统性的回顾梳理与分析；最后讨论了目前面部运动单元检测研究存在的不足以及未来潜在的发展方向。     

基于双离合变速器电控单元的Volcano CAN开发

Volcano 是集汽车电子网络设计、实现和测试于一体的完整工具链。它包括整车网络规划及优化设计工具VNA,网络节点(TCU等)实现工具VTP以及网络测试工具Tellus。本文着重介绍了基于TCU的VTP。     

Lagrangian relaxation hybrid with evolutionary algorithm for short-term generation scheduling

Short-term generation scheduling is an important function in daily operational planning of power systems. It is defined as optimal scheduling of power generators over a scheduling period while respecting various generator constraints and system constraints. Objective of the problem includes costs associated with energy production, start-up cost and shut-down cost along with profits. The resulting problem is a large scale nonlinear mixed-integer optimization problem for which there is no exact solution technique available. The solution to the problem can be obtained only by complete enumeration, often at the cost of a prohibitively computation time requirement for realistic power systems. This paper presents a hybrid algorithm which combines Lagrangian Relaxation (LR) together with Evolutionary Algorithm (EA) to solve the problem in cooperative and competitive energy environments. Simulation studies were carried out on different systems containing various numbers of units. The outcomes from different algorithms are compared with that from the proposed hybrid algorithm and the advantages of the proposed algorithm are briefly discussed.     

High-resolution ISAR imaging of fast rotating targets based on pattern-coupled Bayesian strategy for multiple measurement vectors

Very high resolution inverse synthetic aperture radar (ISAR) imaging of fast rotating targets is a complicated task. There may be insufficient pulses or may introduce migration through range cells (MTRC) during the coherent processing interval (CPI) when we use the conventional range Doppler (RD) ISAR technique. With compressed sensing (CS) technique, we can achieve the high-resolution ISAR imaging of a target with limited number of pulses. Sparse representation based method can achieve the super resolution ISAR imaging of a target with a short CPI, during which the target rotates only a small angle and the range migration of the scatterers is small. However, traditional CS-based ISAR imaging method generally faced with the problem of basis mismatch, which may degrade the ISAR image. To achieve the high resolution ISAR imaging of fast rotating targets, this paper proposed a pattern-coupled sparse Bayesian learning method for multiple measurement vectors, i.e. the PC-MSBL algorithm. A multi-channel pattern-coupled hierarchical Gaussian prior is proposed to model the pattern dependencies among neighboring range cells and correct the MTRC problem. The expectation-maximization (EM) algorithm is used to infer the maximum a posterior (MAP) estimate of the hyperparameters. Simulation results validate the effectiveness and superiority of the proposed algorithm.     

Alteration of the Route to Menaquinone towards Isochorismate-Derived Metabolites

Chorismate and isochorismate constitute branch-point intermediates in the biosynthesis of many aromatic metabolites in microorganisms and plants. To obtain unnatural compounds, we modified the route to menaquinone in Escherichia coli. We propose a model for the binding of isochorismate to the active site of MenD ((1R,2S, 5S,6S)-2-succinyl-5-enolpyruvyl-6-hydroxycyclohex-3-ene-1-carboxylate (SEPHCHC) synthase) that explains the outcome of the native reaction with α-ketoglutarate. We have rationally designed variants of MenD for the conversion of several isochorismate analogues. The double-variant Asn117Arg–Leu478Thr preferentially converts (5S,6S)-5,6-dihydroxycyclohexa-1,3-diene-1-carboxylate (2,3-trans-CHD), the hydrolysis product of isochorismate, with a >70-fold higher ratio than that for the wild type. The single-variant Arg107Ile uses (5S,6S)-6-amino-5-hydroxycyclohexa-1,3-diene-1-carboxylate (2,3-trans-CHA) as substrate with >6-fold conversion compared to wild-type MenD. The novel compounds have been made accessible in vivo (up to 5.3 g L⁻¹). Unexpectedly, as the identified residues such as Arg107 are highly conserved (>94 %), some of the designed variations can be found in wild-type SEPHCHC synthases from other bacteria (Arg107Lys, 0.3 %). This raises the question for the possible natural occurrence of as yet unexplored branches of the shikimate pathway.     

Benchmark value determination of energy efficiency indexes for coal-fired power units based on data mining methods

The operational optimisation of coal-fired power units is important for saving energy and reducing losses in the electric power industry. One of the key issues is how to determine the benchmark values of the energy efficiency indexes of the units. Therefore, a new framework for determining these benchmark values is proposed, based on data mining methods. First, the energy efficiency key performance indicators (KPIs) associated with the net coal consumption rate (NCCR) were selected based on the domain knowledge. Second, the decision-making samples with minimal NCCR were acquired with the fuzzy C-means (FCM) clustering algorithm, and the corresponding clustering centres were employed as the benchmark values. Finally, based on the support vector regression (SVR) algorithm, the target values of the NCCR were obtained with the KPIs as input, and the energy saving potential was evaluated by comparing the target values with the historical values of the NCCR. An actual on-duty 1000 MW unit was taken as study unit, and the results show that the energy saving potential is remarkable when the operators adjust the KPIs based on the calculated benchmark values.