一种跨公司航天软件缺陷预测方法

为提高航天软件测试的效率和质量，针对同公司航天软件数量少、研制周期长的特点，提出了一种跨公司航天软件缺陷预测方法。从航天软件背景信息复杂、规模大、功能独立等特征出发，提出基于静态分类缺陷预测的模型构建思想。引入迁移学习方法，利用最近邻分类器和数据引力模型，对训练数据的分布特征进行修正，提高训练数据与目标数据的相似性；为提高模型的泛化能力以适应目标数据的多样性，提出在训练数据中加入少量目标数据用于模型训练。将该方法在实际工程中进行应用，实验结果表明，与已有软件缺陷预测方法相比，该方法在保持较低误报率（不高于0.3）的情况下可有效提高召回率（接近0.6），整体可信度得到有效增强（G- measure超过0.6），方法稳定度高，泛化能力较强；本方法在实际工程中对测试规模影响可控，测试效率得到提高。     

针对多种处理痕迹的数字语音取证算法

现有的数字语音取证研究主要集中于对单一的某种操作进行检测，无法对不相关的操作进行判断。针对该问题，提出了一种能够同时检测经过变调、低通滤波、高通滤波和加噪这四种操作的数字语音取证方法。首先，计算语音的归一化梅尔频率倒谱系数（MFCC）统计矩特征；然后通过多个二分类器对特征进行训练，并组合投票得到多分类器；最后使用该多分类器对待测语音进行分类。在TIMIT以及UME语音库上的实验结果表明，归一化MFCC统计矩特征在库内实验中均达到了97%以上的检测率，且在对MP3压缩鲁棒性测试的实验中，检测率仍能保持在96%以上。     

涡流空气分级机熵产与分级性能分析

利用热力学第二定律中的熵产理论对涡流空气分级机各不可逆因素引起的熵产进行分析，通过粉料分级试验对其分级性能进行验证，获得了黏性熵产、湍流熵产和壁面熵产分布特点及操作参数对熵产和分级精度的影响规律。熵产分析结果表明，涡流空气分级机内湍流熵产和壁面熵产占总熵产的比例高达56.41%和43.11%，湍流熵产主要产生于转笼叶片间和转笼内部，进风口和细粉出口壁面剪切引起较大壁面熵产；此外，转笼转速和进口风速变化分别仅对转笼区域和切向进风口区域内气流运动熵产影响较大，进口风速-转笼转速处于8.6m/s、 800r/min和18m/s、1200r/min操作工况附近时，涡流空气分级机内总熵产/总能变化率较小，分级流场稳定性较高，对粗、细颗粒分离有利，该工况下分级机的粉料分级试验效果较好，说明熵产理论可用于涡流分级机内流动分析及其操作参数的优化匹配。     

A hybrid knowledge and ensemble classification approach for prediction of venous thromboembolism

Clinical narratives such as progress summaries, lab reports, surgical reports, and other narrative texts contain key biomarkers about a patient's health. Evidence-based preventive medicine needs accurate semantic and sentiment analysis to extract and classify medical features as the input to appropriate machine learning classifiers. However, the traditional approach of using single classifiers is limited by the need for dimensionality reduction techniques, statistical feature correlation, a faster learning rate, and the lack of consideration of the semantic relations among features. Hence, extracting semantic and sentiment-based features from clinical text and combining multiple classifiers to create an ensemble intelligent system overcomes many limitations and provides a more robust prediction outcome. The selection of an appropriate approach and its interparameter dependency becomes key for the success of the ensemble method. This paper proposes a hybrid knowledge and ensemble learning framework for prediction of venous thromboembolism (VTE) diagnosis consisting of the following components: a VTE ontology, semantic extraction and sentiment assessment of risk factor framework, and an ensemble classifier. Therefore, a component-based analysis approach was adopted for evaluation using a data set of 250 clinical narratives where knowledge and ensemble achieved the following results with and without semantic extraction and sentiment assessment of risk factor, respectively: a precision of 81.8% and 62.9%, a recall of 81.8% and 57.6%, an F measure of 81.8% and 53.8%, and a receiving operating characteristic of 80.1% and 58.5% in identifying cases of VTE.     

Rules discovery in fuzzy classifier systems with PSO for scheduling in grid computational infrastructures

Particle swarm optimization (PSO) is a bio-inspired optimization strategy founded on the movement of particles within swarms. PSO can be encoded in a few lines in most programming languages, it uses only elementary mathematical operations, and it is not costly as regards memory demand and running time. This paper discusses the application of PSO to rules discovery in fuzzy classifier systems (FCSs) instead of the classical genetic approach and it proposes a new strategy, Knowledge Acquisition with Rules as Particles (KARP). In KARP approach every rule is encoded as a particle that moves in the space in order to cooperate in obtaining high quality rule bases and in this way, improving the knowledge and performance of the FCS. The proposed swarm-based strategy is evaluated in a well-known problem of practical importance nowadays where the integration of fuzzy systems is increasingly emerging due to the inherent uncertainty and dynamism of the environment: scheduling in grid distributed computational infrastructures. Simulation results are compared to those of classical genetic learning for fuzzy classifier systems and the greater accuracy and convergence speed of classifier discovery systems using KARP is shown.     

Enhanced gravity particle classifier: Experiments with 3D printed device and computational fluid dynamics simulations

Centrifugal force developed in a fluid flow through closed spiral channel produces enhanced gravity environment to facilitate particle classification. The novel design is inspired by open channel spiral concentrators that are used in mineral processing industries. The concept is initially validated through computational fluid dynamics (CFD) simulations. Preferential movement of coarser particles, which experience greater centrifugal force, to the outer periphery was observed. These predictions are validated by conducting experiments on a 3D printed spiral classifier. The CFD simulations compared well with observed experimental separation function. The model was further used to conduct parametric study of various design and operational parameters. Simulations reveal that the cut-size could change from 8 μm to 260 μm depending on the splitter position. The novel device will allow a direct and online control of cut size/density when suitably enhanced with required mechanisms.     

<i>In Silico</i> analysis and linking of metabolism-related genes with the immune landscape in head and neck squamous cell carcinoma

Metabolic reprogramming and immunologic suppression are two critical characteristics promoting the progression of head and neck squamous cell carcinoma (HNSCC). The integrative analysis of all the metabolism-related genes (MRGs) in HNSCC is lacking and the interaction between the metabolism and the immune characteristics also requires more exploration to uncover the potential mechanisms. Therefore, this study was designed to establish a prognostic signature based on all the MRGs in HNSCC. Genes of HNSCC samples were available from the TCGA and GEO databases while the MRGs were retrieved from a previous study. Ultimately 4 prognostic MRGs were selected to construct a model possessing robust prognostic value and accuracy in TCGA cohorts. The favorable reproducibility of this model was confirmed in validation cohorts from GEO databases. The risk score calculated by this model was an independent prognostic factor that further classified these HNSCC patients into high-/low-risk groups. GSEA analyses and somatic mutations indicated the low-risk group could activate several anti-tumor pathways and possessed lower TP53 mutation. The results of ESTIMATE, single-sample GSEA, CIBERSORT, and some immune-related molecules analyses suggested the low-risk group exhibited lower metabolic activities and higher immune characteristics. The Spearman correlation test implied most metabolic pathways with tumor-promoting function were negatively correlated with the immune activity, indicating a plausible approach of combining the anti-metabolism and the immunotherapy drugs in the high-risk group to enhance therapeutic effects than applied separately. In conclusion, this prognostic signature linking MRGs with the immune landscape could promote the individualized treatment for HNSCC patients.     

Methodology for robust multi-parametric control in linear continuous-time systems

This paper presents an extension of the recent multi-parametric (mp-)NCO-tracking methodology by Sun et al. [Comput. Chem. Eng. 92 (2016) 64–77] for the design of robust multi-parametric controllers for constrained continuous-time linear systems in the presence of uncertainty. We propose a robust-counterpart formulation and solution of multi-parametric dynamic optimization (mp-DO), whereby the constraints are backed-off based on a worst-case propagation of the uncertainty using either interval analysis or ellipsoidal calculus and an ancillary linear state feedback. We address the case of additive uncertainty, and we discuss approaches to dealing with multiplicative uncertainty that retain tractability of the mp-NCO-tracking design problem, subject to extra conservativeness. In order to assist with the implementation of these controllers, we also investigate the use of data classifiers based on deep learning for approximating the critical regions in continuous-time mp-DO problems, and subsequently searching for a critical region during on-line execution. We illustrate these developments with the case studies of a fluid catalytic cracking (FCC) unit and a chemical reactor cascade.