Preprocessed dynamic classifier ensemble selection for highly imbalanced drifted data streams

This work aims to connect two rarely combined research directions, i.e., non-stationary data stream classification and data analysis with skewed class distributions. We propose a novel framework employing stratified bagging for training base classifiers to integrate data preprocessing and dynamic ensemble selection methods for imbalanced data stream classification. The proposed approach has been evaluated based on computer experiments carried out on 135 artificially generated data streams with various imbalance ratios, label noise levels, and types of concept drift as well as on two selected real streams. Four preprocessing techniques and two dynamic selection methods, used on both bagging classifiers and base estimators levels, were considered. Experimentation results showed that, for highly imbalanced data streams, dynamic ensemble selection coupled with data preprocessing could outperform online and chunk-based state-of-art methods.     

Wind of change: Small-scale electricity production and distribution-grid efficiency in Sweden

In this paper, we measure the technical efficiency for local electricity distribution firms in Sweden, and in particular how small and micro-scale generation affects efficiency scores. Using a two-stage data envelopment analysis to model the technical efficiency and a double bootstrap approach to estimate the determinants of inefficiencies, we show that firms are heterogeneous in terms of inefficiency, but that a large share of small and micro-scale generation is not associated with more inefficient operations.     

Two-stage optimization for machine learning workflow

Machine learning techniques play a preponderant role in dealing with massive amount of data and are employed in almost every possible domain. Building a high quality machine learning model to be deployed in production is a challenging task, from both, the subject matter experts and the machine learning practitioners.For a broader adoption and scalability of machine learning systems, the construction and configuration of machine learning workflow need to gain in automation. In the last few years, several techniques have been developed in this direction, known as AutoML.In this paper, we present a two-stage optimization process to build data pipelines and configure machine learning algorithms. First, we study the impact of data pipelines compared to algorithm configuration in order to show the importance of data preprocessing over hyperparameter tuning. The second part presents policies to efficiently allocate search time between data pipeline construction and algorithm configuration. Those policies are agnostic from the metaoptimizer. Last, we present a metric to determine if a data pipeline is specific or independent from the algorithm, enabling fine-grain pipeline pruning and meta-learning for the coldstart problem.     

Potential genomic biomarkers of obesity and its comorbidities for phthalates and bisphenol A mixture: <i>In silico</i> toxicogenomic approach

This in silico toxicogenomic study aims to explore the relationship between phthalates and bisphenol A (BPA) co-exposure and obesity, as well as its comorbid conditions, in order to construct a possible set of genomic biomarkers. The Comparative Toxicogenomics Database (CTD; http://ctd.mdibl.org) was used as the main data mining tool, along with GeneMania (https://genemania.org), ToppGene Suite (https://toppgene.cchmc.org) and DisGeNET (http://www.disgenet.org). Among the phthalates, bis(2-ethylhexyl) phthalate (DEHP) and dibutyl phthalate (DBP) were chosen as the most frequently curated phthalates in CTD, which also share similar mechanisms of toxicity. DEHP, DBP and BPA interacted with 84, 90 and 194 obesity-related genes/proteins, involved in 67, 65 and 116 pathways, respectively. Among these, 53 genes/proteins and 42 pathways were common to all three substances. 31 genes/proteins had matching interactions for all three investigated substances, while more than half of these genes/proteins (56.49%) were in co-expression. 7 of the common genes/proteins (6 relevant to humans: CCL2, IL6, LPL, PPARG, SERPINE1, and TNF) were identified in all the investigated obesity comorbidities, while PPARG and LPL were most closely linked to obesity. These genes/proteins could serve as a target for further in vitro and in vivo studies of molecular mechanisms of DEHP, DBP and BPA mixture obesogenic properties. Analysis reported here should be applicable to any mixture of environmental chemicals and any disease present in CTD.     

A novel inverse data driven modelling approach to performance-based building design during early stages

Energy analysis at the early stage of building design is a critical, yet difficult task in performance-based design. The difficulty arises from the complex, iterative, and uncertain nature of building design and the challenges of integration with well-posed energy assessment tools. The purpose of this article is to first review characteristics of performance-based design and establish requirements for a methodology that includes generating promising design alternatives, assessing the energy performance in tandem with the generation of alternatives, and choosing an alternative design solution with confidence. The study then proposes a novel systematic data-driven method, based on linear inverse modeling that generates plausible ranges for design parameters given a preferred energy target. The energy performance in this method is described as a linear function of the design parameters for a particular scenario of design. The application of the proposed method in a case study shows that it is capable of helping designers make informed decisions regarding energy performance iteratively and confidently at the early stages of building design.     

新城市科学背景下的城市设计新可能

本文面对智慧城市和新城市科学 迅速发展的背景，立足新时期城市设计转型 需求，针对新近涌现出的以机器学习、虚拟 现实、计算机可视化等为代表的多种新技术 和以街景数据、兴趣点数据、位置服务数据 等为代表的多源城市数据开展讨论。继而对 其所带来的城市设计新可能进行了探讨和展 望，并对于相关典型工具和代表性案例进行 了介绍。这些伴随新城市科学涌现的数据和 技术不仅能够为城市设计在场地分析、设计 开展和方案评估上带来工作方式的革新，而 且有望进一步明确城市设计的专属技术体 系，并以此推动城市设计的领域构建。     

国土空间规划下水利基础设施信息管理平台设计

加快建立国土空间规划体系并监督实施是党中央、国务院做出的重大部署,而水利基础设施空间布局对促进各类空间布局与水资源承载能力、防洪安全保障水平相适应,预留水利基础设施建设空间具有重要作用。为有效对接国土空间规划编制工作,结合实际需求,研究并建立水利基础设施空间布局管理的标准、规范和体系,完成水利基础设施空间数据库的设计,并研究离线瓦片存储和Lucene全文检索引擎技术。在.Net框架的Visual Studio集成开发环境中,利用ArcGIS Engine组件开发水利基础设施信息管理平台,实现地图浏览、空间数据管理及数据质检分析功能,为统一水利空间用途管控、规划编制审批、实施监督管理提供数据支撑,也为下一步构建基础设施空间布局一张图管控平台提供坚实的基础与保障。     

关于医院数据中心机柜分布规划的探讨

以医院数据中心机柜分布规划进行探讨,对数据中心各个功能区域机柜采用独特的规划方式,来说明有序的、合理的、结构化的规划不仅能满足日常运维管理的便捷,更能紧紧跟随医院信息化的发展。     

线上线下混合模式的实验课程改革——以数据结构课程为例

该文以数据结构课程为例,从课程性质和内容进行介绍,利用线上线下混合式教学,对实验实施改革。以数据分析作为基础进行方法总结,对实验课程内容进行全方位的改革和实施。     

Digital twin-based assembly data management and process traceability for complex products

Complex products such as satellites, missiles, and aircraft typically have demanding requirements for dynamic data management and process traceability. The assembly process for these complex products involves high complexity, strong dynamics, many uncertainties, and frequent rework and repair, especially in the model development stage. Achieving assembly data management and process traceability for complex products has always been a challenge. A recently proposed solution involves one-to-one mapping of the corresponding physical entity, also known as the digital twin method. This paper proposes a digital twin-based assembly data management and process traceability approach for complex products. First, the dynamic evolutionary process of complex product assembly data was analyzed from three dimensions: granularity, period and version. Then, a framework of digital twin-based assembly data management and process traceability for complex products was constructed. Some core techniques are: 1) workflow-based product assembly data organization and version management; 2) synchronous modeling of the product assembly process based on digital twin; and 3) hierarchical management and traceability of product assembly data based on digital twin. On this basis, an algorithm flowchart for generating a product assembly data package was created, which includes product assembly data management, assembly process traceability, and generation of a product assembly data package. Furthermore, the Digital Twin-based Assembly Process Management and Control System (DT-APMCS) was designed to verify the efficiency of the proposed approach. Some aerospace-related assembly enterprises are currently using DT-APMCS and achieving satisfactory results. Finally, a summary of our work is given, and the future research work is also discussed.