Investigating the effect of training–testing data stratification on the performance of soft computing techniques: an experimental study

Abstract

Cross-validation of soft computing techniques needs to be done efficiently to avoid overfitting and underfitting. This is more important in petroleum reservoir characterisation applications where the often-limited training and testing data subsets represent Wells with known and unknown target properties, respectively. Existing data stratification strategies have been haphazardly chosen without any experimental basis. In this study, the optimal training–testing stratification proportions have been rigorously investigated using the prediction of porosity and permeability of petroleum reservoirs as an experimental case. The comparative performances of seven traditional and advanced machine learning techniques were considered. The overall results suggested a recommendable optimum training stratification that could serve as a good reference for researchers in similar applications.     

Analysis and design of a high efficiency bidirectional DC–DC converter for battery and ultracapacitor applications

This paper presents a high efficiency non-isolated bidirectional converter which can be employed as an interface circuit between ultracapacitors or batteries and DC bus voltage. All semiconductor devices in the proposed converter are soft switched while the control circuit remains PWM. So, the energy conversion through the converter is highly efficient. The proposed converter acts as a zero-voltage transition (ZVT) buck to charge an ultracapacitor or battery and acts as a ZVT boost to discharge an ultracapacitor or battery. The performance of the proposed converter with respect to abrupt load and operating mode change is shown through computer simulation results. The results confirm the aforementioned advantages and features of the proposed converter.     

Model predictive control of a DC–DC converter for battery emulation

A battery emulator is used instead of a real traction battery to supply an electric motor inverter on a test bed for hybrid and electric powertrains under deterministic conditions. The use of virtual battery models eliminates the need for expensive battery prototypes. Virtual battery properties such as chemistry, state of charge or state of health can be changed instantly. However, the control of a battery emulator is a challenging problem. Very fast reference tracking is required for battery impedance emulation but motor inverters act as constant power loads that have a negative influence on the tracking performance and can even lead to instability. In this paper an MPC strategy is proposed for solving this problem. Scheduling of local controllers is utilized in order to handle the nonlinear and destabilizing load. Furthermore, a fast algorithm is presented that allows real-time MPC subject to input and output constraints. Experimental results obtained with a battery emulator supplying an electric drive inverter demonstrate the performance of the stabilizing controller.     

An approach to design and implementation of on-chip clock generator for the switched capacitor based embedded DC–DC converter

Here, the design and implementation of an on-chip clock generator which is needed for a switched capacitor based embedded DC–DC converter is described. The strategies that should be taken during making the design by predicting the occurrence of the parasitic issues at the time of implementation to keep the performance of the clock generator at per in silicon are also elaborated. The reported measurement results closely match with the simulation results in clock generation. It can be a helpful tutorial paper to design and implement an on-chip clock generator suitable for mid-frequency, real time applications.     

The verification and analysis on the results of the video retrieval system

The retrieval of video information is a key multimedia technology, which has been paid wide-range attention recently. This paper introduces the verification and analysis of video information results in the video retrieval system from three aspects： first, the way of the browse and navigation; second, video summary; third, display and interaction interface.     

The effect of online store atmosphere on consumer's emotional responses – an experimental study of music and colour

The current study is a convergence of two research orientations: the effect of ambient factors (e.g. music and colour) in physical stores and the website design in cyber context. The former emphasises the influence of sensory stimuli on the shoppers' responses; whereas the latter address the relationship between website design factors (e.g. usability) and the performance of a virtual store. This article aims to bridge the gap between the above research orientations and explores the impact of two environmental elements – music and colour – of an online store on the consumers' emotions – considered as direct antecedents to shopping behaviours – by employing a laboratory experiment. The results indicated that both music and colour reveal significant effects on respondents' emotional responses. To be more specific, participants felt more aroused and pleasant when they were under fast music and warm colour conditions than those who were exposed to an environment with slow music and cool colour. In addition, the congruency of these two atmospheric factors enhances the effects of atmosphere on people's emotional responses.     

Robust digital control of a DC–DC buck converter with low frequency samplings

A robust DC?CDC converter which can covers extensive load change and also input voltage changes with one controller is needed. Then the demand to suppress output voltage change becomes still severer. We propose an approximate 2-degree-of-freedom (2DOF) digital controller which realized start-up response and dynamic load response independently. The controller makes a control bandwidth wider, and at the same time makes variations of the output voltage small at sudden changes of a load and an input voltage. In this paper, a new approximate 2DOF digital control system with additional zeros is proposed. Using the additional zeros, the second-order differential transfer characteristics between equivalent disturbances and a output voltage are realized. Therefore, the new controller makes variations of the output voltage smaller and the sudden changes of the load and the input voltage. This controller is actually implement on a DSP and is connected to the DC?CDC converter. Experimental results demonstrate that this type of digital controller can satisfy given severe specifications with low frequency sampling.     

Modelling the Evolution of National Economies Based on Input–Output Networks

Uncovering the evolutionary dynamics of economies is helpful for us to design economic policy. This paper develops an economic evolution model by examining the coupled dynamics of industry growth and interindustry structure. For each industry, its economic properties (mainly characterized by price and quantity) are incorporated into the model. The input–output relationships among different industries are described as input–output networks, in which nodes represent industries, and weights represent technological and economic constraints between pairing industries. By measuring the dynamic importance of each node, we find that all the nodes in the input–output networks have the same dynamic importance. On the basis of this empirical regularity and the rational expectation assumption, we show that the coupled dynamics of the economic properties of nodes and input–output networks can explain the evolutionary dynamics of national economies.     

The effect of Facebook use on office workers’ job performance and the moderating effects of task equivocality and interdependence

As office workers’ use of social networking sites (SNSs) has increased, so has research interest in the effect of SNS use on job performance. The present study employs data collected from South Korean office workers to examine how the use of the SNS Facebook affects job performance and to investigate the moderating effects of task characteristics (task equivocality and task interdependence). The results show that Facebook use for work has a positive effect on job performance, although the time spent on Facebook use does not have a significant effect on job performance. Moreover, task interdependence is associated with a decrease in the effect of Facebook use for work on job performance. In other words, task interdependence has a negative moderating effect on the impact of Facebook use for work on job performance. The reason is that Facebook is particularly advantageous for enhancing performance in tasks where the level of interdependence is low because it is a medium with relatively low synchrony and is unsuitable for one-to-one relationship building. This study has implications for companies that are concerned about formulating policies related to employees’ use of SNSs.     

Maximum power tracking of a generic photovoltaic system via a fuzzy controller and a two-stage DC–DC converter

This study presents a new two-stage DC–DC converter for maximum power point tracking (MPPT) and a voltage boost of a generic photovoltaic (PV) system. An intelligent MPPT of PV system based on fuzzy logic control (FLC) is presented to adaptively design the proposed fuzzy controlled MPPT controller (FC-MPPTC) while a voltage boost controller (VBC) is used to fix the output voltage to a voltage level that is higher than the required operating voltage to the back-end grid impedance. Modeling and simulation on the PV system and the DC–DC converter circuit are achieved by state-space and the software Powersim. The PV string considered has the rated power around 600?VA under varied partial shadings. The FC-MPPTC and VBC are designed and realized by a DSP module (TMS320F2812) to adjust the duty cycle in the two-stage DC–DC converter. A special FLC algorithm is forged to render an MPPT faster and more accurate than conventional MPPT technique, perturb and observe (P&O). The simulations are intended to validate the performance of the proposed FC-MPPTC. Experiments are conducted and results show that MPPT can be achieved in a fast pace and the efficiency reaches over 90?%, even up to 96?%. It is also found that the optimized tracking speed of the proposed FC-MPPTC is in fact more stable and faster than the general P&O method with the boost voltage capable of offering a stable DC output.     

Human–automation interaction for multiple robot control: the effect of varying automation assistance and individual differences on operator performance

In a human–automation interaction study, automation assistance level (AL) was investigated for its effects on operator performance in a dynamic, multi-tasking environment. Participants supervised a convoy of manned and unmanned vehicles traversing a simulated environment in three AL conditions, while maintaining situation awareness and identifying targets. Operators’ situation awareness, target detection performance, workload and individual differences were evaluated. Results show increasing AL generally improved task performance and decreased perceived workload, however, differential effects due to operator spatial ability and perceived attentional control were found. Eye-tracking measures were useful in parsing out individual differences that subjective measures did not detect. At the highest AL, participants demonstrated potentially complacent behaviour, indicating task disengagement.

Practitioner Summary: The effect of varying automation assistance level (AL) on operator performance on multiple tasks were examined in a within-subjects experiment. Findings indicated a moderate AL improved performance, while higher levels encouraged complacent behaviour. Effects due to individual differences suggest that effective AL depends on the underlying characteristics of the operator.     

Deflection of coupled elasticity–electrostatic bimorph PVDF material: theoretical,FEM and experimental verification

Piezoelectric materials have wide applications in the field of mechanical, aerospace and civil engineering because of its voltage dependent actuation. Piezoelectric material goes through voltage generation whenever deflection is induced in it and vice versa. Piezoelectric bimorph beam has been widely used for sensing and actuating. In the actuation mode, an electric field is applied across the beam thickness, one layer contracts while the other expands. This results in the bending of the entire structure and tip deflection. In the sensing mode, the bimorph is used to measure an external load by monitoring the piezoelectric induced electrode voltages. In this research work, a 2D bimorph piezoelectric actuator model having two layers made of polyvinylidene fluoride (PVDF) material was developed to examine the inverse piezoelectric effect. Finite element analysis (FEA) was carried out on specially designed actuator model by using MATLAB Partial Differential Equation (PDE) Toolbox™. Theoretical analysis has been carried out to measure the tip deflection under applied electric field. The laboratory test was performed to investigate the deformation behavior of piezoelectric actuator. It is observed that, more the electric field applied, more the material would be deformed in a particular direction. The experimental results are in good agreement with numerical results.

     

Modelling the dynamics of the students’ academic performance in the German region of the North Rhine-Westphalia: an epidemiological approach with uncertainty

Student academic underachievement is a concern of paramount importance in Europe, where around 15% of the students in the last high school courses do not achieve the minimum knowledge academic requirement. In this paper, we propose a model based on a system of differential equations to study the dynamics of the students’ academic performance in the German region of the North Rhine-Westphalia. This approach is supported by the idea that both good and bad study habits, are a mixture of personal decisions and influence of classmates. This model allows us to forecast the student academic performance by means of confidence intervals over the next few years.     

Thermal–infrared emissivities of natural surfaces: improvements on the experimental set-up and new measurements

Ground measurements of thermal infrared emissivities of terrestrial surfaces are required to derive accurate temperatures from radiometric measurements, and also to apply and validate emissivity models using satellite sensor observations. This paper focuses on the demanding aspects that are involved in the field measurement of emissivity using the box method and a hand-held radiometer. Measuring emissivities in field conditions can be hampered by external factors such as wind and solar irradiance. This can increase the time spent on the field campaign but, most importantly, it can cause no-sense fluctuations between consecutive observations. Here we propose original developments for the experimental instrumentation to ensure consistency of measurements. Moreover, we present a dataset of emissivity values for different soils, rocks and vegetation samples measured in the 8–14, 8.2–9.2, 10.5–1 1.5 and 11.5–12.5 µm wavebands.     

Analysis of submarine steering: effects of cognitive and perceptual–motor requirements on the mental workload and performance of helmsmen

The purpose of the study is to model manual submarine steering and its effects on helmsmen in terms of performance and mental workload. This activity is first formalized according to (a) cognitive requirements, by identifying different levels of control, and (b) perceptual–motor requirements, by analysing the directional compatibility of control–display design. An experiment is then carried out on a simulator designed by a world leader in military naval shipbuilding. This experiment follows a unique scenario including two driving situations with different levels of cognitive requirements (approach and stabilization phases). It is achieved by two groups, each carrying out a perceptual–motor task on a specific steering control–display configuration proposed by the naval shipbuilder (one with a standard numeric display and one with a new visual–spatial representation, both tasks controlled by the same joystick). The findings of this study show that the cognitive requirements during the stabilization phase with high propulsion speed produce increased mental workload, and the perceptual–motor requirements also produce increased mental workload when a direction-of-motion stereotype is violated (upward–forward relationship).     

Crowdsourcing contests: understanding the effect of competitors’ participation history on their performance

Crowdsourcing contests have become increasingly important and prevalent with the ubiquity of the Internet. Designing efficient crowdsourcing contests is not possible without the deep understanding of the factors affecting individuals’ continuous participation and their performance. Prior studies have mainly focused on identifying the effect of task-specific, environment-specific, organisation-specific, and individual-specific factors on individuals’ performance in crowdsourcing contests. And to our knowledge, there are no or very few studies on evaluating the effect of individuals’ participation history on their performance. This paper aims to address this research gap using a data set from TopCoder. This study derives competitors’ participation history factors, such as participation frequency, participation recency, winning frequency, winning recency, tenure, and last performance to construct models depicting effects of these factors on competitors’ performance in online crowdsourcing contests. The research findings demonstrate that most of competitors’ participation history factors have significant effect on their performance. This paper also indicates that competitors’ participation frequency and winning frequency moderate the relationship between last performance and performance, and relationship between tenure and performance positively. On the other hand, individuals’ participation recency and winning recency moderate relationship between last performance and performance negatively, but have no significant effect on the relationship between tenure and performance.     

Commerce-oriented revenue models for content providers: an experimental study of commerciality’s effect on credibility

If content providers want to build successful businesses on the Internet, they have to establish viable revenue models online. Because selling content or ads is less profitable online than offline, content providers have begun to generate revenues by selling products or services related to their content. However, this incentivizes content providers to increase sales by manipulating their content and thus may harm the content’s credibility. We conducted a vignette-based online experiment to test the effect of content providers’ revenue models on the credibility of two different types of content. Although our results revealed significant differences between revenue models for one of the content types, we did not find evidence that users distrust content providers employing commerce-oriented revenue models. Our findings shed light on the relationship between credibility and monetization of content on the Internet and provide helpful insights for practitioners in the media industry regarding optimal revenue generation strategies.     

Predictions of the Al-rich region of the Al–Co–Ni–Y system based upon first-principles and experimental data

A thermodynamic database has been produced for the Al–Co–Ni–Y quaternary system, with an emphasis on the Al-rich region of the Al–Ni–Y ternary system. The database was created using the CALPHAD method, combining existing binary systems with relevant experimental and first-principles information for selected Al–Ni–Y and Co-containing compounds. The thermodynamic database was used to produce equilibrium and non-equilibrium Scheil simulations to determine the phases present in Al–Co–Ni–Y alloys. The values for the Scheil simulation show good agreement, when compared with experimentally determined phase fractions of intermetallic particles dispersed in an Al matrix for three Al-rich quaternary alloys.