Transport Map sampling with PGD model reduction for fast dynamical Bayesian data assimilation

The motivation of this work is to address real-time sequential inference of parameters with a full Bayesian formulation. First, the proper generalized decomposition (PGD) is used to reduce the computational evaluation of the posterior density in the online phase. Second, Transport Map sampling is used to build a deterministic coupling between a reference measure and the posterior measure. The determination of the transport maps involves the solution of a minimization problem. As the PGD model is quasi-analytical and under a variable separation form, the use of gradient and Hessian information speeds up the minimization algorithm. Eventually, uncertainty quantification on outputs of interest of the model can be easily performed due to the global feature of the PGD solution over all coordinate domains. Numerical examples highlight the performance of the method.     

基于模糊谱聚类的不确定蛋白质相互作用网络功能模块挖掘

针对谱聚类融合模糊C-means（FCM）聚类的蛋白质相互作用（PPI）网络功能模块挖掘方法准确率不高、执行效率较低和易受假阳性影响的问题，提出一种基于模糊谱聚类的不确定PPI网络功能模块挖掘（FSC-FM）方法。首先，构建一个不确定PPI网络模型，使用边聚集系数给每一条蛋白质交互作用赋予一个存在概率测度，克服假阳性对实验结果的影响；第二，利用基于边聚集系数流行距离（FEC）策略改进谱聚类中的相似度计算，解决谱聚类算法对尺度参数敏感的问题，进而利用谱聚类算法对不确定PPI网络数据进行预处理，降低数据的维数，提高聚类的准确率；第三，设计基于密度的概率中心选取策略（DPCS）解决模糊C-means算法对初始聚类中心和聚类数目敏感的问题，并对预处理后的PPI数据进行FCM聚类，提高聚类的执行效率以及灵敏度；最后，采用改进的边期望稠密度（EED）对挖掘出的蛋白质功能模块进行过滤。在酵母菌DIP数据集上运行各个算法可知，FSC-FM与基于不确定图模型的检测蛋白质复合物（DCU）算法相比，F-measure值提高了27.92%，执行效率提高了27.92%；与在动态蛋白质相互作用网络中识别复合物的方法（CDUN）、演化算法（EA）、医学基因或蛋白质预测算法（MGPPA）相比也有更高的F-measure值和执行效率。实验结果表明，在不确定PPI网络中，FSC-FM适合用于功能模块的挖掘。     

Data sharing mechanism of various mineral resources based on blockchain

Basins with various mineral resources coexisting and enriching often occupy an important strategic position. The exploration of various mineral resources is repetitive at present due to unshared data and imperfect management mechanism. This situation greatly increases the cost of energy exploitation in the country. Traditional data-sharing mode has several disadvantages, such as high cost, difficulty in confirming the right of data, and lack of incentive mechanism, which make achieving real data sharing difficult. In this paper, we propose a data-sharing mechanism based on blockchain and provide implementation suggestions and technical key points. Compared with traditional data-sharing methods, the proposed data-sharing mechanism can realize data sharing, ensure data quality, and protect intellectual property. Moreover, key points in the construction are stated in the case study section to verify the feasibility of the data-sharing system based on blockchain proposed in this paper.     

Operational time-series data modeling via LSTM network integrating principal component analysis based on human experience

Today’s information technologies involve increasingly intelligent systems, which come at the cost of increasingly complex equipment. Modern monitoring systems collect multi-measuring-point and long-term data which make equipment health prediction a “big data” problem. It is difficult to extract information from such condition monitoring data to accurately estimate or predict health statuses. Deep learning is a powerful tool for big data processing that is widely utilized in image and speech recognition applications, and can also provide effective predictions in industrial processes. This paper proposes the Long Short-term Memory Integrating Principal Component Analysis based on Human Experience (HEPCA-LSTM), which uses operational time-series data for equipment health prognostics. Principal component analysis based on human experience is first conducted to extract condition parameters from the condition monitoring system. The long short-term memory (LSTM) framework is then constructed to predict the target status. Finally, a dynamic update of the prediction model with incoming data is performed at a certain interval to prevent any model misalignment caused by the drifting of relevant variables. The proposed model is validated on a practical case and found to outperform other prediction methods. It utilizes a powerful deep learning analysis method, the LSTM, to fully process big condition monitoring series data; it effectively extracts the features involved with human experience and takes dynamic updates into consideration.     

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.     

Smart firefighting construction in China: Status,problems, and reflections

“Smart firefighting” construction as a part of the “smart city” has been a concern of the public security and fire agencies at all levels. In this study, the status, problems, and reflections of “smart firefighting” construction in China are discussed. A recent survey indicates that China has launched its smart firefighting construction and initially created a new perspective on its regional smart firefighting work based on three main aspects: intelligent disaster perception by Internet of Things (IoT) construction, intelligent disaster prevention by big data construction, and intelligent disaster disposal by emergency rescue platform construction. However, the current smart firefighting construction in China still has some prominent problems such as the data interconnectivity and normalized management of various platforms, the extensibility of smart firefighting platforms, and the intelligent level of smart firefighting researches, which need to be solved urgently. Therefore, we argue that smart firefighting construction in China should establish data interconnectivity, industrial normalized management, 2D/3D geographic information interaction and extension, high-integration fire protection theory, and many other aspects in the near future and truly realize firefighting visualization and efficient data applications for 4D time space. This study could provide valuable reference for smart firefighting and smart city construction.     

Using electroencephalogram to continuously discriminate feelings of personal thermal comfort between uncomfortably hot and comfortable environments

Thermal comfort is an important factor for the design of buildings. Although it has been well recognized that many physiological parameters are linked to the state of thermal comfort or discomfort of humans, how to use physiological signal to judge the state of thermal comfort has not been well studied. In this paper, the feasibility of continuously determining feelings of personal thermal comfort was discussed by using electroencephalogram (EEG) signals in private space. In the study, 22 subjects were exposed to thermally comfortable and uncomfortably hot environments, and their EEG signals were recorded. Spectral power features of the EEG signals were extracted, and an ensemble learning method using linear discriminant analysis or support vector machine as a sub-classifier was used to build the discriminant model. The results show that an average discriminate accuracy of 87.9% can be obtained within a detection window of 60 seconds. This study indicates that it is feasible to distinguish whether a person feels comfortable or too hot in their private space by multi-channel EEG signals without interruption and suggests possibility for further applications in neuroergonomics.     

基于MF-R和AWS密钥管理机制的物联网健康监测大数据分析系统

带有传感器的可穿戴式医疗设备不断生成大量数据，由于数据的复杂性，难以通过处理和分析大数据来找到有价值的决策信息。为了解决这个问题，提出了一种新的物联网体系结构，用于存储和处理医疗应用的可扩展传感器数据（大数据）。所提出的架构主要由两个子架构组成：Meta Fog重定向（MF-R）架构和AWS密钥管理机制。MF-R架构使用Apache Pig和Apache HBase等大数据技术来收集和存储不同传感器设备生成的传感器数据，并利用卡尔曼滤波消除噪声。AWS密钥管理机制使用密钥管理方案，目的是保护云中的数据，防止未经授权的访问。当数据存储在云中时，所提出的系统能够使用随机梯度下降算法和逻辑回归来开发心脏病的预测模型。仿真实验表明，和其他几种算法相比，提出的算法具有更小的误差，且在吞吐量、准确度等方面具有一定的优越性。     

基于SVM的煤与瓦斯突出预测模型及应用

为有效预测矿井内煤与瓦斯突出的危险程度,对其影响因素做了分析与探讨,分别构建了基于粒子群优化算法以及遗传算法支持向量机的煤与瓦斯突出预测模型,并且通过实例对两种模型预测的准确性进行了验证。分别利用单项以及综合指标、BP神经网络以及PSO-SVM模型、GA-SVM模型,对寺河煤矿二号井的突出区域进行预测比较。结果表明,PSO-SVM的预测模型不仅可以在小样本数据中预测出煤与瓦斯突出程度的大小,而且综合预测结果更加精确,其在解决矿井内煤与瓦斯突出的小样本数据中显示出更加强大、通用的性能。     

Development and monitoring of an integrated bioprocess for production of a potential malaria vaccine with Pichia pastoris

An engineered variant of the yeast Pichia pastoris was used to produce the potential malaria vaccine D1M1. This paper describes the implementation of an expanded bed adsorption chromatography step into a sequential cultivation process of the yeast in order to link protein expression, cell release, and product capture of the secreted protein in a fully automated plant. The process is operated with a semi-continuous strategy for an integrated production. Process improvements have been achieved using design of experiments. Resulting purities of product achieved up to 87% with recoveries of 51% in a single downstream operation. Furthermore, a multivariate analysis of historical batch data was used to develop a golden batch model for process monitoring.