Extant Methods Research Articles

Adaptive Aquila Optimization Controlled Deep Convolutional Neural Network for Power Management in Supercapacitors/Battery of Electric Vehicles

Electric Vehicles (EVs) may be a viable solution to reduce the huge energy consumption and greenhouse emissions of global transportation. However, the cost and range of batteries are two major obstacles for EV. An efficient Power management system for EVs, which includes Supercapacitor (SC) and battery with an optimized converter, is proposed in this paper. An optimal Direct Current (DC)-DC Bi-directional Buck-Boost Converter (BBBC) with a Proportional Integral Derivative (PID) controller is used for the optimal flow of power from the energy source to the drive during EV acceleration. The regenerative braking energy is allowed to return through the same bidirectional converter and retained in the Hybrid Energy Storage System (HESS) during the deceleration mode. A novel optimization is attained in the converter controller circuit using a Deep Convolution Neural Network (DCNN) and Adaptive Aquila Optimization Algorithm (AAqOA). The proposed strategy is validated using the results compared to conventional algorithms. In particular, the settling time of the suggested AAqOA model is 55.44%, 96.94%, 97.03%, and 91.87% better than the extant PI, DA, SSA, and AOA methods, respectively.

Selection framework of visualization methods in designing AR industrial task-support systems

An Augmented reality (AR) task-support system incorporates head-mounted displays (HMDs) to improve human performance in maintenance, assembly, and disassembly tasks by intuitively showing the working procedure to the operator. To achieve the intended AR capability and to enable the operator to work efficiently, a system designer must understand the characteristics of AR and design the information to be shown operators for each subtask, taking into account the working situation represented by the procedure, operator performance skills, workspace, devices, and operating objects (i.e., AR information design). Especially, in the AR information design, the designer needs AR expertize to select the suitable visualization method among the many extant methods. This is difficult for designers (manual writers) to perform AR information design in factories in the future. However, at present, only a few studies have been conducted to select the suitable visualization method for each subtask. This study proposes to define 31 subtask types as criteria for decomposing tasks in AR information design. Furthermore, we classify and define 42 visualization methods in terms of AR information design. Finally, to select the suitable visualization method for each subtask, we construct a selection framework consisting of three selection categories representing the working status and 17 selection conditions. The evaluation experiments of the proposed framework could output an average of 4.3 suitable visualization method candidates, including at least one suitable visualization method selected by AR experts in the subtask working situation. By incorporating the proposed framework into a website and combining it with existing HMDs and services for AR application development, it is expected that designers will be able to develop appropriate AR task-support systems.

The differential measure for Pythagorean fuzzy multiple criteria group decision-making

Pythagorean fuzzy sets (PFSs) proved to be powerful for handling uncertainty and vagueness in multi-criteria group decision-making (MCGDM). To make a compromise decision, comparing PFSs is essential. Several approaches were introduced for comparison, e.g., distance measures and similarity measures. Nevertheless, extant measures have several defects that can produce counter-intuitive results, since they treat any increase or decrease in the membership degree the same as the non-membership degree; although each parameter has a different implication. This study introduces the differential measure (DFM) as a new approach for comparing PFSs. The main purpose of the DFM is to eliminate the unfair arguments resulting from the equal treatment of the contradicting parameters of a PFS. It is a preference relation between two PFSs by virtue of position in the attribute space and according to the closeness of their membership and non-membership degrees. Two PFSs are classified as identical, equivalent, superior, or inferior to one another giving the degree of superiority or inferiority. The basic properties of the proposed DFM are given. A novel method for multiple criteria group decision-making is proposed based on the introduced DFM. A new technique for computing the weights of the experts is developed. The proposed method is applied to solve two applications, the evaluation of solid-state drives and the selection of the best photovoltaic cell. The results are compared with the results of some extant methods to illustrate the applicability and validity of the method. A sensitivity analysis is conducted to examine its stability and practicality.

Exploring the influence of supervisor and family work support on salespeople’s engagement and unethical behaviors

PurposeSalespeople’s unethical behaviors have been the subject of extensive academic research and practitioner outcry. High pressure, complex selling environments and extant methods of monitoring, control and compensation of salespeople have been found to lead to short-term sales behaviors, such as lying, that are detrimental to both customers and firms in the long run. Furthermore, work and family pressures can lead to unethical sales behaviors. However, research on the impact of the social environment on unethical behaviors in sales is scant. This study aims to examine the impact of social factors (e.g. supervisor support and family work support) on salespeople’s unethical behaviors as a social exchange process in an emerging market context where work and family pressures are high. Specifically, the mediating role of emotional and cognitive engagement on the relationship between social support and unethical behaviors is investigated.Design/methodology/approachAn empirical study was conducted to examine the relationship between social support (family work support and supervisor support), engagement (emotional and cognitive) and unethical behaviors. Survey data were collected from 496 salespeople from multiple industries in India, and partial least squares structural equation modeling was used to test the hypothesized relationships. In addition, post hoc qualitative interviews were conducted with 15 salespeople to corroborate the findings.FindingsSupervisor support is positively related to emotional and cognitive engagement and negatively related to unethical behaviors. Contrary to our hypothesis, family work support is positively related to unethical behaviors. However, this relationship becomes negative when the salesperson is emotionally and cognitively engaged with their work.Research limitations/implicationsThis research enhances the understanding of the antecedents of unethical behaviors in sales. Supervisor support, emotional engagement and cognitive engagement reduce unethical behaviors. However, family work support increases unethical behaviors. The relationship between social support (supervisor and family work) and unethical behaviors is mediated by emotional and cognitive engagement. These findings offer sales managers dealing with increasing work and family pressures and the blurring of personal and professional life a way to motivate their sales force to act in a manner that benefits customers and the firm in the long run.Practical implicationsThe findings offer insights on how sales managers and organizations can help design supportive work environments for their salespeople to help reduce unethical behaviors. The findings also highlight the importance of understanding salesperson family values during the hiring process and keeping salespeople engaged, especially while they work from home, are isolated from their work environment and spend more working hours at home with family members.Originality/valueTo the best of the authors’ knowledge, the current research is the first to investigate the impact of family work support on unethical behaviors. This is timely and valuable as the current COVID-19 pandemic has increased the number of salespeople working from home, reduced sales performance and increased anxiety due to economic uncertainty, all of which could encourage unethical sales behaviors. This paper is also the first to investigate the mediating role of engagement on the effects of social support on unethical behaviors.

Distribution-free estimation of individual parameter logit (IPL) models using combined evolutionary and optimization algorithms

When estimating random coefficients models from choice data, decisions relating to the multivariate density function assumed to describe preference heterogeneity across the population raise questions about stochastic (in)dependence between preference dimensions, uni- vs. multi-modality, potential point masses, bounds and/or constraints on support regions, among other concerns. Parametric representations of population distributions have generally implied uncomfortable compromises to achieve estimation tractability. It would seem preferable to sidestep such issues by estimating individual preferences in a distribution-free manner, but this freedom of form implies a large number of parameters since we lose the parsimony enabled by parametric densities and must deal directly with estimation of individual decision maker preferences. I propose a hybrid distribution-free estimator for individual parameter logit models that uses a genetic algorithm as first stage, the solution from which becomes a starting point for a gradient-based search to obtain the final posterior maximum likelihood estimates of individual preferences. This estimator is described in detail, its parameter recovery capability is tested with Monte Carlo data generation simulations, and a case study is developed in some detail to illustrate its use in policy analysis. The estimator can be applied to both stated and revealed preference data, requiring only that sufficient choice replications be available for individual observation units consistent with extant estimation methods. Computational experience shows the estimator to require CPU times comparable to extant simulation-based estimation methods, meaning that its use is practical for the exploration of the parameter space through multiple trials.

Conducting large‐scale mixed‐method research on harm and abuse prevention with children under 12: Learning from a UK feasibility study

AbstractThis paper reports on a feasibility study for an evaluation of a UK primary school‐based prevention programme that addresses multiple forms of abuse and neglect, identifying research design and ethical issues and exploring research practice. For this feasibility study, 194 children aged 6–11 years completed a baseline survey and 113 did so following the intervention. Eight focus groups were undertaken with 52 children and nine interviews with school staff. We highlight key considerations for conducting large‐scale mixed‐method research on sensitive topics with younger children, a focus that is largely absent from the extant research methods literature. The feasibility study showed that younger children can contribute their views on sensitive topics in ways that are measurable, replicable and reliable, contesting ideas that certain topics are too sensitive to explore with younger children.

Review of Fundamental Active Current Extraction Techniques for SAPF.

The field of advanced digital signal processing methods is one of the fastest developing scientific and technical disciplines, and is important in the field of Shunt Active Power Filter control methods. Shunt active power filters are highly desirable to minimize losses due to the increase in the number of nonlinear loads (deformed power). Currently, there is rapid development in new adaptive, non-adaptive, and especially hybrid methods of digital signal processing. Nowadays, modern methods of digital signal processing maintain a key role in research and industrial applications. Many of the best practices that have been used to control shunt active power in industrial practice for decades are now being surpassed in favor of new progressive approaches. This systematic research review classifies the importance of using advanced signal processing methods in the field of shunt active power filter control methods and summarizes the extant harmonic extraction methods, from the conventional approach to new progressive methods using genetic algorithms, artificial intelligence, and machine learning. Synchronization techniques are described and compared as well.

Reassessing the dependence between economic growth and financial conditions since 1973

SummaryAdrian, Boyarchenko and Giannone ((2019), ABG) adapt quantile regression (QR) methods to examine the relationship between US economic growth and financial conditions. We confirm their empirical findings, using their methodology and their pre‐2016 sample. Mindful of the importance of the Covid‐19 pandemic, we extend the sample to 2021Q3 and find attenuation of the key estimated coefficients using ABG's empirical methods. Given the pandemic observations, we provide robust QR analysis of dependence based on ranked data and explain the relationship with extant copula modelling methods.

Service configuration optimization for multiple customers considering service process information and time-varying service resources

Service configuration is an important enabling technology designed to achieve mass customization and provide customers with the most suitable service. Extant optimization-based service configuration methods, which provide customers with the optimal configuration by establishing an optimization model based on a modular structure, have various limitations. The impact of the service process information on the configuration and the constraints of time-varying service resources are not considered. Moreover, simultaneous multiple customer configuration is not considered. In this study, a service configuration optimization model for multiple customers considering service process information and time-varying service resource constraints was established based on quality function deployment (QFD). The model was transformed into a linear model to facilitate determination of a solution. It was then extended by considering uncertainty in the QFD and further transformed into a triple-objective model. A space-partitioning algorithm and non-dominated sorting genetic algorithm (NSGA-II) were developed to obtain the exact Pareto set of the triple-objective model for small-scale and non-dominated solutions for large-scale problems, respectively. A case study and numerical experiments were performed to verify the effectiveness of the proposed approach, and the results show that the two developed algorithms performed well. Decision support systems based on the proposed models and algorithms can help a service company provide customized services to improve customer satisfaction and increase market share.

A novel alpha-level sets based fuzzy DEMATEL method considering experts’ hesitant information

Fuzzy DEMATEL method is diffusely employed to analyze the interrelationship among factors in various fields under uncertain and fuzzy environment. In the extant fuzzy DEMATEL studies, fuzzy assessments are converted into related crisp values by means of different defuzzification ways. Such conversion may result in not only the loss of information, but also the discount of consideration of fuzzy information. Therefore, it seems reasonable and necessary to keep as much information as possible during the analysis process, instead of converting it into crisp values at the very beginning. An appropriate way to keep as much information as possible is to employ alpha level sets to handle fuzzy information instead of simple defuzzification. In addition, it is quite common that experts may hesitate under uncertain and fuzzy environment in the real-world situation, when providing their assessments on the interrelationship among factors. However, such practical issue is neglected in the extant fuzzy DEMATEL methods. With respect to aforementioned limitations, this study proposes a novel alpha level sets based fuzzy DEMATEL method to handle the fuzzy information, together with considering experts’ hesitation from qualitative context under uncertain and fuzzy environment. Additionally, two different options are provided to analyze the interrelationship among factors in the proposed method. The proposed method not only improves the extant fuzzy DEMATEL studies, but also enriches the theoretical studies of fuzzy DEMATEL, its novelty and superiority is demonstrated through illustrative example and related comparisons.

Robust contrast enhancement method using a retinex model with adaptive brightness for detection applications.

Low light image enhancement with adaptive brightness, color and contrast preservation in degraded visual conditions (e.g., extreme dark background, lowlight, back-light, mist. etc.) is becoming more challenging for machine cognition applications than anticipated. A realistic image enhancement framework should preserve brightness and contrast in robust scenarios. The extant direct enhancement methods amplify objectionable structure and texture artifacts, whereas network-based enhancement approaches are based on paired or large-scale training datasets, raising fundamental concerns about their real-world applicability. This paper presents a new framework to get deep into darkness in degraded visual conditions following the fundamental of retinex-based image decomposition. We separate the reflection and illumination components to perform independent weighted enhancement operations on each component to preserve the visual details with a balance of brightness and contrast. A comprehensive weighting strategy is proposed to constrain image decomposition while disrupting the irregularities of high frequency reflection and illumination to improve the contrast. At the same time, we propose to guide the illumination component with a high-frequency component for structure and texture preservation in degraded visual conditions. Unlike existing approaches, the proposed method works regardless of the training data type (i.e., low light, normal light, or normal and low light pairs). A deep into darkness network (D2D-Net) is proposed to maintain the visual balance of smoothness without compromising the image quality. We conduct extensive experiments to demonstrate the superiority of the proposed enhancement. We test the performance of our method for object detection tasks in extremely dark scenarios. Experimental results demonstrate that our method maintains the balance of visual smoothness, making it more viable for future interactive visual applications.

DeepZF: improved DNA-binding prediction of C2H2-zinc-finger proteins by deep transfer learning.

Cys2His2 zinc-finger (C2H2-ZF) proteins are the largest class of human transcription factors and hence play central roles in gene regulation and cell function. C2H2-ZF proteins are characterized by a DNA-binding domain containing multiple ZFs. A subset of the ZFs bind diverse DNA triplets. Despite their central roles, little is known about which of their ZFs are binding and how the DNA-binding preferences are encoded in the amino acid sequence of each ZF. We present DeepZF, a deep-learning-based pipeline for predicting binding ZFs and their DNA-binding preferences given only the amino acid sequence of a C2H2-ZF protein. To the best of our knowledge, we compiled the first in vivo dataset of binding and non-binding ZFs for training the first ZF-binding classifier. Our classifier, which is based on a novel protein transformer, achieved an average AUROC of 0.71. Moreover, we took advantage of both in vivo and in vitro datasets to learn the recognition code of ZF-DNA binding through transfer learning. Our newly developed model, which is the first to utilize deep learning for the task, achieved an average Pearson correlation greater than 0.94 over each of the three DNA binding positions. Together, DeepZF outperformed extant methods in the task of C2H2-ZF protein DNA-binding preferences prediction: it achieved an average Pearson correlation of 0.42 in motif similarity compared with an average correlation smaller than 0.1 achieved by extant methods. By applying established interpretability techniques, we show that DeepZF inferred biologically relevant binding principles, such as the effect of amino acid residue positions on ZF DNA-binding potential. DeepZF code, model, and results are available via github.com/OrensteinLab/DeepZF. Supplementary data are available at Bioinformatics online.

Reconstruction of Coronal Magnetic Fields Using a Poloidal–Toroidal Representation

A new method for reconstruction of coronal magnetic fields as force-free fields (FFFs) is presented. Our method employs poloidal and toroidal functions to describe divergence-free magnetic fields. This magnetic field representation naturally enables us to implement the boundary conditions at the photospheric boundary, i.e., the normal magnetic field and the normal current density there, in a straightforward manner. At the upper boundary of the corona, a source surface condition can be employed, which accommodates magnetic flux imbalance at the bottom boundary. Although our iteration algorithm is inspired by extant variational methods, it is nonvariational and requires far fewer iteration steps than most others. The computational code based on our new method is tested against the analytical FFF solutions by Titov & Démoulin. It is found to excel in reproducing a tightly wound flux rope, a bald patch, and quasi-separatrix layers with a hyperbolic flux tube.

An improved Grey Wolf algorithm for optimal placement of unified power flow controller

Most crucial techniques for power system operation as well as control is Optimal Power Flow (OPF) that establishes the lowest operating costs and keeps the control variables within safe ranges. Furthermore, bus voltage and power flow across a power system are controlled by a device called a Unified Power Flow Controller (UPFC) and it is one of the most promising Flexible AC Transmission Systems (FACTS) devices for load flow control. Due to the necessary adjustments to take into account the UPFC characteristics, solving optimal power flow (OPF) problems with UPFC is a crucial and challenging task. Hence, this work intends to introduce a new Grey Wolf with Populace-based Update Evaluation (GW-PUE) algorithm for optimal placement of UPFC to achieve OPF.Different objective functions like minimization of power loss, voltage profile deviation and UPFC cost are consideredfor solving the placement problem. Moreover, the adoptedapproach is an improved form of the traditional Grey Wolf Optimization (GWO).At last, the adopted model is tested on the standard IEEE 5, IEEE 14 as well as IEEE 30 bus system. The performance of the suggested work is contrasted with extant methods in terms ofvarious measures. Especially, thecomputation time of the adopted GW-PUE method in IEEE 5 bus system is 59.61%, 14.85%, 1.33%, and 16.29% higher than the existing FF-CS, BBO, FF, and MSSA methods, respectively.

GCN-based stock relations analysis for stock market prediction.

Most stock price predictive models merely rely on the target stock’s historical information to forecast future prices, where the linkage effects between stocks are neglected. However, a group of prior studies has shown that the leverage of correlations between stocks could significantly improve the predictions. This article proposes a unified time-series relational multi-factor model (TRMF), which composes a self-generating relations (SGR) algorithm that can extract relational features automatically. In addition, the TRMF model integrates stock relations with other multiple dimensional features for the price prediction compared to extant works. Experimental validations are performed on the NYSE and NASDAQ data, where the model is compared with the popular methods such as attention Long Short-Term Memory network (Attn-LSTM), Support Vector Regression (SVR), and multi-factor framework (MF). Results show that compared with these extant methods, our model has a higher expected cumulative return rate and a lower risk of return volatility.

Testing for Serial Correlation in Autoregressive Exogenous Models with Possible GARCH Errors.

Autoregressive exogenous, hereafter ARX, models are widely adopted in time series-related domains as they can be regarded as the combination of an autoregressive process and a predictive regression. Within a more complex structure, extant diagnostic checking methods face difficulties in remaining validity in many conditions existing in real applications, such as heteroscedasticity and error correlations exhibited between the ARX model itself and its exogenous processes. For these reasons, we propose a new serial correlation test method based on the profile empirical likelihood. Simulation results, as well as two real data examples, show that our method has a good performance in all mentioned conditions.

Semi-supervised shadowed sets for three-way classification on partial labeled data

Shadowed set divides a fuzzy set into three regions through fuzzy-rough transformation to denote acceptance, rejection and uncertain decision. Based on the tri-partition property, shadowed sets are utilized to implement the machine learning methods for uncertain data analysis. The extant uncertain machine learning methods with shadowed sets include the unsupervised clustering on only unlabeled data and the supervised classification on only labeled data. However, for the partial labeled data containing both labeled and unlabeled data instances, the studies of uncertain learning methods with shadowed sets are very limited. Aiming at the requirement, in this paper, we propose a novel semi-supervised shadowed set on partial labeled data and thereby construct semi-supervised shadowed neighborhoods to implement the three-way classification of uncertain data. To construct the semi-supervised shadowed set, we reformulate the objective function of shadowed sets, in which the membership loss in fuzzy-rough transformation is weighted by labeled and unlabeled data. We also analyze the influence of labeled data to the shadowed set construction. Experiments validate that the proposed three-way classification method with semi-supervised shadowed sets is effective to utilize partial labeled data to achieve low-risk uncertain data classification.

MixPatch: A New Method for Training Histopathology Image Classifiers

CNN-based image processing has been actively applied to histopathological analysis to detect and classify cancerous tumors automatically. However, CNN-based classifiers generally predict a label with overconfidence, which becomes a serious problem in the medical domain. The objective of this study is to propose a new training method, called MixPatch, designed to improve a CNN-based classifier by specifically addressing the prediction uncertainty problem and examine its effectiveness in improving diagnosis performance in the context of histopathological image analysis. MixPatch generates and uses a new sub-training dataset, which consists of mixed-patches and their predefined ground-truth labels, for every single mini-batch. Mixed-patches are generated using a small size of clean patches confirmed by pathologists while their ground-truth labels are defined using a proportion-based soft labeling method. Our results obtained using a large histopathological image dataset shows that the proposed method performs better and alleviates overconfidence more effectively than any other method examined in the study. More specifically, our model showed 97.06% accuracy, an increase of 1.6% to 12.18%, while achieving 0.76% of expected calibration error, a decrease of 0.6% to 6.3%, over the other models. By specifically considering the mixed-region variation characteristics of histopathology images, MixPatch augments the extant mixed image methods for medical image analysis in which prediction uncertainty is a crucial issue. The proposed method provides a new way to systematically alleviate the overconfidence problem of CNN-based classifiers and improve their prediction accuracy, contributing toward more calibrated and reliable histopathology image analysis.

Prediction of Suspended Sediment Concentration Based on the Turbidity-Concentration Relationship Determined via Underwater Image Analysis

Sediment measurement data are essential for sediment transport analysis and therefore highly important in overall river planning. Extant sediment measurement methods consume considerable manpower and time and are limited by factors including economic reasons and worker risks. This study primarily aimed to predict the changes in SSC (Suspended Sediment Concentration) and turbidity by examining the change in color in underwater images. While maintaining a constant flow in a channel, the turbidity and concentration were measured under different SSC. Multiple regression models were developed using turbidity measurement results, and they exhibited high explanatory powers (adjusted R2 > 0.91). Furthermore, upon verification using the verification dataset of the experimental results, an excellent predictive power (RMSE ≈ 0.4 NTU) was demonstrated. The model with the highest predictive power, which was inclusive of red and green bands and showed no underlying multicollinearity was used to predict turbidity. Finally, the turbidity and suspended sediment concentration relationship determined from the experimental results was used to estimate the sediment concentration from the color changes in the underwater images. The concentrations that were predicted by the model showed satisfactory results, compared to the measurements (RMSE ≈ 21 ppm). This study indicated the feasibility of continuous SSC monitoring using underwater images as a new measurement method.

Prediction of Cell-Penetrating Peptides Using a Novel HSIC-Based Multiview TSK Fuzzy System

Cell-penetrating peptides (CPPs) are short peptides that can carry cargo into cells. CPPs are widely utilized due to their powerful loading capacity and transduction efficiency. Identifying CPPs is the basis for studying their functions and mechanisms; however, experimental methods to identify CPPs are expensive and time-consuming. Recently, CPP predictors based on machine learning methods have become a research hotspot. Although considerable progress has been made, some challenges remain unresolved. First, most predictors employ a variety of feature descriptors to transform an original sequence into multiview data; however, extant methods ignore the relationships between different views, limiting further performance improvement. Second, most machine learning models are actually black boxes and cannot offer insightful advice. In this paper, a novel Hilbert–Schmidt independence criterion (HSIC)-based multiview TSK fuzzy system is proposed. Compared with other machine learning methods, TSK fuzzy systems have better interpretability, and the introduction of multiview mechanisms provides comprehensive insight into the intrinsic laws of the data. HSIC is utilized here to measure the independence and enhance the complementarity between different views. Notably, the proposed method attained prediction accuracy results of 92.2% and 96.2% for the training and independent test sets, respectively. The empirical results show that our promising approach features greater recognition performance than the state-of-the-art method.