Search results

The purpose of this paper is to improve the existing differential evolution (DE) mutation operator so as to accelerate its convergence.

A new general donor form for mutation operation in DE is presented, which defines a donor as a convex combination of the triplet of individuals selected for a mutation. Three new donor schemes from that form are deduced.

The three donor schemes were empirically compared with the original DE version and three existing variants of DE by using a suite of nine well‐known test functions, and were also demonstrated by a practical application case – training a neural network to approximate aerodynamic data. The obtained numerical simulation results suggested that these modifications to the mutation operator could improve the DE's convergence performance in both the convergence rate and the convergence reliability.

Further research is still needed for adequately explaining why it was possible to simultaneously improve both the convergence rate and the convergence reliability of DE to that extent despite the well‐known “No Free Lunch” theorem. Also further research is considered necessary for outlining more distinctively the particular class of problems, where the current observations can be generalized.

More complicated engineering problems could be solved sub‐optimally, whereas their real optimal solution may never be reached subject to the current computer capability.

Though DE has demonstrated a considerably better convergence performance than the other evolutionary algorithms (EAs), its convergence rate is still far from what is hoped for by scientists. On the one hand, a higher convergence rate is always expected for any optimization method used in seeking the global optimum of a non‐linear objective function. On the other hand, since all EAs, including DE, work with a population of solutions rather than a single solution, many evaluations of candidate solutions are required in the optimization process. If evaluation of candidate solutions is too time‐consuming, the overall optimization cost may become too expensive. One often has to limit the algorithm to operate within an acceptable time, which maybe is not enough to find the global optimum (optima), but enough to obtain a sub‐optimal solution. Therefore, it is continuously necessary to investigate the new strategies to improve the current DE algorithm.

To present and validate a new differential evolution (DE) method for multi‐objective optimization method.

A new selection scheme was designed to replace the existing one in DE to enable DE applicable to either single objective or multi‐objective optimizations.

The new method was validated with three simple multi‐objective optimization problems. The simulation results show that the approach is capable of generating an approximated Pareto‐front for each selected problem. The new DE method was used to optimize a prototype air mixer subject to two objective functions to be minimized. The results demonstrate that the new DE approach can handle this practical multi‐objective problem successfully.

The new method is an easy‐to‐implement evolutionary method and has the potential for application for any complicated engineering optimizations.

Genetic algorithms have been extensively used in different domains as a type of robust optimization method. They have a much better chance of achieving global optima than conventional gradient‐based methods which usually converge to local sub‐optima. However, convergence speeds of genetic algorithms are often not good enough at their current stage. For this reason, improving the existing algorithms becomes a very important aspect of accelerating the development of the algorithms. Three improved strategies for genetic algorithms are proposed based on Holland’s simple genetic algorithm (SGA). The three resultant improved models are studied empirically and compared, in feasibility and performance evaluation, with a set of artificial test functions which are usually used as performance benchmarks for genetic algorithms. The simulation results demonstrate that the three proposed strategies can significantly improve the SGA.

Although governments have used social media platforms to interact with the public in an attempt to minimize anxiety and provide a forum for public discussion during the pandemic, governments require sufficient crisis communication skills to engage citizens in taking appropriate action effectively. This study aims to examine how the National Health Commission of China (NHCC) has used TikTok, the leading short video–based platform, to facilitate public engagement during COVID-19.

Building upon dual process theories, this study integrates the activation of information exposure, prosocial interaction theory and social sharing of emotion theory to explore how public engagement is related to message sensation value (MSV), media character, content theme and emotional valence. A total of 354 TikTok videos posted by NHCC were collected during the pandemic to explore the determinants of public engagement in crises.

The findings demonstrate that MSV negatively predicts public engagement with government TikTok, but that instructional information increases engagement. The presence of celebrities and health-care professionals negatively affects public engagement with government TikTok accounts. In addition, emotional valence serves a moderating role between MSV, media characters and public engagement.

Government agencies must be fully aware of the different combinations of MSV and emotion use in the video title when releasing crisis-related videos. Government agencies can also leverage media characters – health professionals in particular – to enhance public engagement. Government agencies are encouraged to solicit public demand for the specific content of instructing information through data mining techniques.

Despite the extensive academic interest in social media sentiment for financial fields, multimodal data in the stock market has been neglected. The purpose of this paper is to explore the influence of multimodal social media data on stock performance, and investigate the underlying mechanism of two forms of social media data, i.e. text and pictures.

This research employs panel vector autoregressive models to quantify the effect of the sentiment derived from two modalities in social media, i.e. text information and picture information. Through the models, the authors examine the short-term and long-term associations between social media sentiment and stock performance, measured by three metrics. Specifically, the authors design an enhanced sentiment analysis method, integrating random walk and word embeddings through Global Vectors for Word Representation (GloVe), to construct a domain-specific lexicon and apply it to textual sentiment analysis. Secondly, the authors exploit a deep learning framework based on convolutional neural networks to analyze the sentiment in picture data.

The empirical results derived from vector autoregressive models reveal that both measures of the sentiment extracted from textual information and pictorial information in social media are significant leading indicators of stock performance. Moreover, pictorial information and textual information have similar relationships with stock performance.

To the best of the authors’ knowledge, this is the first study that incorporates multimodal social media data for sentiment analysis, which is valuable in understanding pictures of social media data. The study offers significant implications for researchers and practitioners. This research informs researchers on the attention of multimodal social media data. The study’s findings provide some managerial recommendations, e.g. watching not only words but also pictures in social media.

The purpose of this paper is to describe a method permitting the creation of a realistic model of spherical roller bearing with the aim of determining contact stress and fatigue life based on dynamic loading conditions. The paper also aims to recognize the effect of tolerance values on contact stress and fatigue life. Motion and load transmission in spherical roller bearing occurs within the assembly by elliptical curved contacting surfaces. The stress produced by the transmitted load would be very high because of least contacting area between these surfaces.

The paper describes a methodology to determine contact stress using analytically as well as finite element method for spherical roller bearing. The comparison for the both each approach for contact stress at different loading condition is carried out. Prediction of fatigue life based on dynamic loading conditions for bearing is also determined using finite element model. The effect on induced contact stress and fatigue life by varying tolerances on inner race dimensions have been found out.

The paper suggests that the maximum stress produces at the start or end of the contacting arc under static loading condition in spherical roller bearing. The analytical and finite element approach is in good agreement. The fatigue life prediction is useful for selecting loading conditions for various applications of double row spherical roller bearing. Tolerance level at inner ring raceway radius is kept high because of manufacturing constrain of complex curvature geometric shape.

The present approach does not consider dynamic loading conditions for contact stress analysis. Therefore, researchers are encouraged to analyze the effect of wear, lubrication and other tribological aspects on bearing life.

The paper includes determination of contact stress and prediction of fatigue life for spherical roller bearing using analytical as well as finite element approach. The tolerance values at inner race are identified as per manufacturing constraint based on contact stress and fatigue life.

Recommending suitable doctors to patients on healthcare consultation platforms is important to both the patients and the platforms. Although doctor recommendation methods have been proposed, they failed to explain recommendations and address the data sparsity problem, i.e. most patients on the platforms are new and provide little information except disease descriptions. This research aims to develop an interpretable doctor recommendation method based on knowledge graph and interpretable deep learning techniques to fill the research gaps.

This research proposes an advanced doctor recommendation method that leverages a health knowledge graph to overcome the data sparsity problem and uses deep learning techniques to generate accurate and interpretable recommendations. The proposed method extracts interactive features from the knowledge graph to indicate implicit interactions between patients and doctors and identifies individual features that signal the doctors' service quality. Then, the authors feed the features into a deep neural network with layer-wise relevance propagation to generate readily usable and interpretable recommendation results.

The proposed method produces more accurate recommendations than diverse baseline methods and can provide interpretations for the recommendations.

This study proposes a novel doctor recommendation method. Experimental results demonstrate the effectiveness and robustness of the method in generating accurate and interpretable recommendations. The research provides a practical solution and some managerial implications to online platforms that confront information overload and transparency issues.

The purpose of this paper is to draw on triadic reciprocal determinism and social exchange theory to examine how “induced-type” and “compulsory-type” union participation influence union commitment and job involvement, and how union participation in the west differs from that in China. It also examines whether the role of both organizational justice and employee participation climate (EPC) functions in the Chinese context.

Cross-sectional data are collected from 694 employees in 46 non-publicly owned enterprises, both Chinese and foreign, in the Pearl River Delta region of China. A multi-level moderated mediation test is used to examine the model of this research.

Union participation is positively related to organizational justice, union commitment and job involvement. In addition, organizational justice acts as the mediator among union participation, union commitment and job involvement. Specifically, the mediating role of organizational justice between union participation and union commitment, and between union participation and job involvement, is stronger in high-EPC contexts than low-EPC contexts.

Instead of examining the impacts of attitudes on union participation, as per most studies in the western context, this research examines the impacts of union participation in the Chinese context on attitudes, including union commitment and job involvement. It also reveals the role of both organizational justice and EPC in the process through which union participation influences union commitment and job involvement.