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.     

Assessing the impact of COVID-19 and safety parameters on energy project performance with an analytical hierarchy process

COVID-19 has destabilized the global economy, disrupted the lives of billions of people globally, and caused the workforce to suffer. Furthermore, the spread of this disease has caused most nations to impose strict lockdown regulations and shutdown most industries. This study aimed to highlight the key issues of energy project performance alongside construction activities that were halted during the COVID-19 outbreak to follow social distancing, lockdown, and public safety parameters. A questionnaire survey was administered to accomplish the purpose of this study. The responses of 42 energy project professionals and experts were evaluated using the analytical hierarchy process (AHP) for group decision-making. AHP shows that the biggest influences on project performance during COVID-19 pandemic were government measures and personal factors. The findings provide insight to support energy project planning and management during and after the pandemic, including prioritization of labor force health and safety.     

单片机与接口技术项目化教学改革的实践与探索

As a comprehensive electrical and electronic course, Single Chip Microcomputer and Interface Technology is usually com- bined with automation technology, applied electronic technology, communication technology, etc., so that students can master the professional theory and application practice of single chip microcomputer. In the course teaching, teachers mainly focus on the knowledge points of single chip microcomputer system design, application programming, installation and debugging, select suitable interface circuit, application program, and organize and design the integrated circuit system and logic function of single chip micro- computer, so as to help students complete the resource allocation and function realization of different single chip microcomputer project design.     

How does a bank's involvement interplay with a firm's capacity investment? An analysis and comparison of different consortium structures

As nonrecourse project finance (rather than financing on a sovereign basis) is becoming more prevalent worldwide, financing institutions have to collaborate more closely with firms to optimize capacity‐investment and financing decisions. Under this background, this paper presents a stylized Stackelberg games model, taking into account the firm's capacity investment as well as the bank's interest rate and funding ratio decisions. Consortium structures between bank and firm are formalized into five modes based on industry practice, namely, the integrated consortium, pure shareholder funding, bank as leader, full coordination, and bank as follower. The optimality and equilibrium of each of the five modes are analytically derived, and their existence and uniqueness are demonstrated. Valuable economic insights are obtained through both modeling analysis and numerical experiments, with the main findings including the following: (i) a lack of bank financing leads to insufficient capacity investment and poor consortium performance; (ii) interest rate and funding ratio play important but different roles in the bank's risk management; (iii) the bank's proactivity in leading and coordinating the consortium is critical for the two parties’ overall performance; and (iv) if the bank is the follower, the firm's capacity decision is irrelevant to the bank's loan contract, and the consortium cannot be coordinated to the first‐best level of performance.     

Field Performance of High Oleic Soybeans with Mutant FAD2-1A and FAD2-1B Genes in Tennessee

Soybean [Glycine max (L.) Merr.] oil with high oleic acid (>75%) has increased oxidative stability and health benefits that are valuable for food, fuel, and industrial products. It has been determined that two naturally occurring mutations in genes FAD2-1A and FAD2-1B can combine to produce high oleic soybeans. The objective of this study was to test the effect of these mutant alleles on seed yield and oil and protein concentration. Molecular markers assisted in the creation of a population of 48 BC₃F_2:4 lines (93.75% expected genome commonality). Each line was classified into one of four genotypic groups where both FAD2-1A and FAD2-1B genes were either homozygous wild type or mutant, respectively. Twelve lines for each genotypic group were evaluated in three replications at six locations across Tennessee. There was no seed yield difference between the high oleic genotypic group and the other groups (P < 0.05). On the other hand, there were differences in fatty acid profiles and oil and protein concentrations. In combination, the mutant FAD2-1A and FAD2-1B alleles produced a mean of 803.1 g kg⁻¹ oleic acid. This is, on average, approximately 500 g kg⁻¹ more oleic acid compared to soybean lines with only one mutant FAD2-1 allele. The high oleic double mutant group had more total oil (228.0 g kg⁻¹) and protein (401.0 g kg⁻¹) compared to all other genotypic groups (P < 0.05). Overall, this specific combination of mutant FAD2-1A and FAD2-1B alleles appears to generate conventional high oleic soybeans without a yield drag.     

The dynamics of systems integration: Balancing stability and change on London's Crossrail project

Systems integration is essential for the design and execution of large, complex projects, but relatively little is known about how this task develops over time during the life cycle of a project. This paper builds on the concept of “disciplined flexibility” to describe how systems integration can be conceived as a dynamic process of maintaining stability, while responding flexibly to changing conditions. We examine the dynamics of systems integration through a case-study of Crossrail, the construction of London's new urban railway system, which will be called the Elizabeth Line when it opens for service. The balancing act of stability and change manifests during critical periods of the project life cycle as various interdependent systems evolve with different degrees of maturity. We identify how various types of reciprocal interdependencies in complex projects such as Crossrail – at the system and system of systems levels – require ongoing monitoring and control, and the mutual adjustment of tasks.     

基于CPET时序聚类的中长跑耐力运动员选拔方法

心肺运动试验（CPET）能将人体的呼吸系统、心血管系统等综合为一体，不仅能够体现受试者的有氧运动能力，评估受试者的心肺耐力，而且能以整体整合医学的视角来研究受试者对运动的应激反应。为对CPET数据进行凝聚层次聚类分析，提出一种基于时间序列形态特征的算法。选取15名业余中长跑运动员的CPET数据作为聚类对象，聚类指标选取了表征有氧能力和心肺耐量的耗氧量、二氧化碳、心率、分钟通气当量、代谢当量、生理死腔与潮气量比值、呼吸商及每搏输出量等8类指标，体现运动员摄取、利用氧的效率、肺循环以及心功能等综合状况。通过聚类分析发现受试者个体差异较大，未出现明显的“群居分布”特征，根据轮廓系数评估可剔除心肺耐量较差的测试者。实验结果表明，该算法在确保聚类准确率的同时能够降低数据压缩率，且对形态特征显著的数据集进行聚类效果更佳。     

A Feature Selection Strategy to Optimize Retinal Vasculature Segmentation

Diabetic retinopathy (DR) is a complication of diabetes mellitus that appears in the retina. Clinitians use retina images to detect DR pathological signs related to the occlusion of tiny blood vessels. Such occlusion brings a degenerative cycle between the breaking off and the new generation of thinner and weaker blood vessels. This research aims to develop a suitable retinal vasculature segmentation method for improving retinal screening procedures by means of computer-aided diagnosis systems. The blood vessel segmentation methodology relies on an effective feature selection based on Sequential Forward Selection, using the error rate of a decision tree classifier in the evaluation function. Subsequently, the classification process is performed by three alternative approaches: artificial neural networks, decision trees and support vector machines. The proposed methodology is validated on three publicly accessible datasets and a private one provided by Hospital Sant Joan of Reus. In all cases we obtain an average accuracy above 96% with a sensitivity of 72% in the blood vessel segmentation process. Compared with the state-of-the-art, our approach achieves the same performance as other methods that need more computational power. Our method significantly reduces the number of features used in the segmentation process from 20 to 5 dimensions. The implementation of the three classifiers confirmed that the five selected features have a good effectiveness, independently of the classification algorithm.