Search results

1 – 9 of 9
Per page
102050
Citations:
Loading...
Access Restricted. View access options
Article
Publication date: 4 July 2024

Weijiang Wu, Heping Tan and Yifeng Zheng

Community detection is a key factor in analyzing the structural features of complex networks. However, traditional dynamic community detection methods often fail to effectively…

96

Abstract

Purpose

Community detection is a key factor in analyzing the structural features of complex networks. However, traditional dynamic community detection methods often fail to effectively solve the problems of deep network information loss and computational complexity in hyperbolic space. To address this challenge, a hyperbolic space-based dynamic graph neural network community detection model (HSDCDM) is proposed.

Design/methodology/approach

HSDCDM first projects the node features into the hyperbolic space and then utilizes the hyperbolic graph convolution module on the Poincaré and Lorentz models to realize feature fusion and information transfer. In addition, the parallel optimized temporal memory module ensures fast and accurate capture of time domain information over extended periods. Finally, the community clustering module divides the community structure by combining the node characteristics of the space domain and the time domain. To evaluate the performance of HSDCDM, experiments are conducted on both artificial and real datasets.

Findings

Experimental results on complex networks demonstrate that HSDCDM significantly enhances the quality of community detection in hierarchical networks. It shows an average improvement of 7.29% in NMI and a 9.07% increase in ARI across datasets compared to traditional methods. For complex networks with non-Euclidean geometric structures, the HSDCDM model incorporating hyperbolic geometry can better handle the discontinuity of the metric space, provides a more compact embedding that preserves the data structure, and offers advantages over methods based on Euclidean geometry methods.

Originality/value

This model aggregates the potential information of nodes in space through manifold-preserving distribution mapping and hyperbolic graph topology modules. Moreover, it optimizes the Simple Recurrent Unit (SRU) on the hyperbolic space Lorentz model to effectively extract time series data in hyperbolic space, thereby enhancing computing efficiency by eliminating the reliance on tangent space.

Details

International Journal of Intelligent Computing and Cybernetics, vol. 17 no. 3
Type: Research Article
ISSN: 1756-378X

Keywords

Access Restricted. View access options
Article
Publication date: 22 July 2024

Yifeng Zheng, Xianlong Zeng, Wenjie Zhang, Baoya Wei, Weishuo Ren and Depeng Qing

As intelligent technology advances, practical applications often involve data with multiple labels. Therefore, multi-label feature selection methods have attracted much attention…

42

Abstract

Purpose

As intelligent technology advances, practical applications often involve data with multiple labels. Therefore, multi-label feature selection methods have attracted much attention to extract valuable information. However, current methods tend to lack interpretability when evaluating the relationship between different types of variables without considering the potential causal relationship.

Design/methodology/approach

To address the above problems, we propose an ensemble causal feature selection method based on mutual information and group fusion strategy (CMIFS) for multi-label data. First, the causal relationship between labels and features is analyzed by local causal structure learning, respectively, to obtain a causal feature set. Second, we eliminate false positive features from the obtained feature set using mutual information to improve the feature subset reliability. Eventually, we employ a group fusion strategy to fuse the obtained feature subsets from multiple data sub-space to enhance the stability of the results.

Findings

Experimental comparisons are performed on six datasets to validate that our proposal can enhance the interpretation and robustness of the model compared with other methods in different metrics. Furthermore, the statistical analyses further validate the effectiveness of our approach.

Originality/value

The present study makes a noteworthy contribution to proposing a causal feature selection approach based on mutual information to obtain an approximate optimal feature subset for multi-label data. Additionally, our proposal adopts the group fusion strategy to guarantee the robustness of the obtained feature subset.

Details

International Journal of Intelligent Computing and Cybernetics, vol. 17 no. 4
Type: Research Article
ISSN: 1756-378X

Keywords

Access Restricted. View access options
Article
Publication date: 31 July 2024

Yongqing Ma, Yifeng Zheng, Wenjie Zhang, Baoya Wei, Ziqiong Lin, Weiqiang Liu and Zhehan Li

With the development of intelligent technology, deep learning has made significant progress and has been widely used in various fields. Deep learning is data-driven, and its…

48

Abstract

Purpose

With the development of intelligent technology, deep learning has made significant progress and has been widely used in various fields. Deep learning is data-driven, and its training process requires a large amount of data to improve model performance. However, labeled data is expensive and not readily available.

Design/methodology/approach

To address the above problem, researchers have integrated semi-supervised and deep learning, using a limited number of labeled data and many unlabeled data to train models. In this paper, Generative Adversarial Networks (GANs) are analyzed as an entry point. Firstly, we discuss the current research on GANs in image super-resolution applications, including supervised, unsupervised, and semi-supervised learning approaches. Secondly, based on semi-supervised learning, different optimization methods are introduced as an example of image classification. Eventually, experimental comparisons and analyses of existing semi-supervised optimization methods based on GANs will be performed.

Findings

Following the analysis of the selected studies, we summarize the problems that existed during the research process and propose future research directions.

Originality/value

This paper reviews and analyzes research on generative adversarial networks for image super-resolution and classification from various learning approaches. The comparative analysis of experimental results on current semi-supervised GAN optimizations is performed to provide a reference for further research.

Details

International Journal of Intelligent Computing and Cybernetics, vol. 17 no. 4
Type: Research Article
ISSN: 1756-378X

Keywords

Access Restricted. View access options
Article
Publication date: 7 May 2024

Yifeng Zhang and Min-Xuan Ji

The aim of this study is to discern the role of digital finance in driving rural industrial integration and revitalization. Specifically, it intends to shed light on how the deep…

175

Abstract

Purpose

The aim of this study is to discern the role of digital finance in driving rural industrial integration and revitalization. Specifically, it intends to shed light on how the deep development of digital finance can contribute to the optimization and transformation of the rural industrial structure. The research further explores the particular effects of this financial transformation in the central and western regions of China.

Design/methodology/approach

This research studies the influence of digital finance on rural industrial integration across 30 Chinese provinces from 2011 to 2020. Utilizing the entropy weight method, a comprehensive evaluation index system is established to gauge the level of rural industrial integration. A two-way fixed effects model, intermediary effect model, and threshold effect model are employed to decipher the relationship between digital finance and rural industrial integration.

Findings

Findings reveal a positive relationship between digital finance and rural industrial integration. A single threshold feature was identified: beyond a traditional finance development level, the marginal effect of digital finance on rural industrial integration increases. These effects are more noticeable in central and western regions.

Originality/value

Empirical outcomes contribute to policy discourse on rural digital finance, assisting policymakers in crafting effective strategies. Understanding the threshold of traditional finance development provides a new perspective on the potential of digital finance to drive rural industrial integration.

Details

China Agricultural Economic Review, vol. 16 no. 3
Type: Research Article
ISSN: 1756-137X

Keywords

Available. Open Access. Open Access
Article
Publication date: 14 May 2024

Ying Hu and Feng’e Zheng

The ancient town of Lijiang is a representative place of ethnic minorities in China’s southwest border area jointly built by many ethnic groups. Its rich and diversified history…

313

Abstract

Purpose

The ancient town of Lijiang is a representative place of ethnic minorities in China’s southwest border area jointly built by many ethnic groups. Its rich and diversified history, culture and architecture as well as its artistic and spiritual values need to be better retained and explored.

Design/methodology/approach

The protection and inheritance of Lijiang’s cultural heritage will be improved through the construction of digital memory resources. To guide Lijiang’s digital memory construction, this study explores strategies of digital memory construction by analyzing four case studies of well-known memory projects from China and America.

Findings

From the case studies analysis, factors of digital memory construction were identified and compared. Factors led to the discussion of strategies for constructing the digital memory of Lijiang within its design, construction and service phases.

Originality/value

The ancient town of Lijiang is a famous historical and cultural city in China, and it is also a representative place of ethnic minorities in the border area jointly built by many ethnic groups. The rich culture should be preserved and digitalized to offer better use for the whole nation.

Access Restricted. View access options
Article
Publication date: 2 July 2024

Wenfang Lin, Yifeng Wang, Georges Samara and Jintao Lu

The sustainable development of the platform economy has been hindered by the absence and alienation of platform corporate social responsibility. Previous studies have mainly…

543

Abstract

Purpose

The sustainable development of the platform economy has been hindered by the absence and alienation of platform corporate social responsibility. Previous studies have mainly focused on the contents and governance models for platform corporate social responsibility. This study seeks to explore which strategy participants choose in the governance of platform corporate social responsibility and their influencing factors.

Design/methodology/approach

Using a platform ecosystem approach, a quadrilateral evolutionary game model was developed, and the stabilities of subjects’ behavioral strategies and their combinations in various scenarios were analyzed. Additionally, the effects of key parameters on the system’s evolutionary path were simulated.

Findings

The ideal steady state system is achieved when platform enterprises, complementors and consumers adopt positive strategies while the government adopts lax regulation. Moreover, the evolutionary strategies of the subjects are influenced by several factors, including the participation costs of governance, the rewards and punishments imposed by platform enterprises, as well as the reputational losses of platform enterprises and complementors due to media coverage.

Practical implications

This study offers insights into improving the governance effectiveness of platform corporate social responsibility for managers and practitioners.

Originality/value

This study contributes to existing literature by considering the rational orientation of platform ecosystem members and revealing the interaction mechanisms among members. Furthermore, this study combines collective action theory and reputation theory to clarify the influencing factors on members’ behaviors.

Access Restricted. View access options
Article
Publication date: 29 September 2022

Yifeng Zhu, Ziyang Zhang, Hailong Zhao and Shaoling Li

Five-level rectifiers have received widespread attention because of their excellent performance in high-voltage and high-power applications. Taking a five-level rectifier with…

90

Abstract

Purpose

Five-level rectifiers have received widespread attention because of their excellent performance in high-voltage and high-power applications. Taking a five-level rectifier with only four-IGBT for this study, a sliding mode predictive control (SMPC) algorithm is proposed to solve the problem of poor dynamic performance and poor anti-disturbance ability under the traditional model predictive control with the PI outer loop.

Design/methodology/approach

First, mathematical models under the two-phase stationary coordinate system and two-phase synchronous rotating coordinate system are established. Then, the design of the outer-loop sliding mode controller is completed by establishing the sliding mode surface and design approach rate. The design of the inner-loop model predictive controller was completed by discretizing the mathematical model equations. The modulation part uses a space vector modulation technique to generate the PWM wave.

Findings

The sliding mode predictive control strategy is compared with the control strategy with a PI outer loop and a model predictive inner loop. The proposed control strategy has a faster dynamic response and stronger anti-interference ability.

Originality/value

For the five-level rectifier, the advantages of fast dynamic influence and parameter insensitivity of sliding mode control are used in the voltage outer loop to replace the traditional PI control, and which is integrated with the model predictive control used in the current inner loop to form a novel control strategy with a faster dynamic response and stronger immunity to disturbances. This novel strategy is called sliding mode predictive control (SMC).

Details

Circuit World, vol. 50 no. 1
Type: Research Article
ISSN: 0305-6120

Keywords

Access Restricted. View access options
Article
Publication date: 7 March 2022

Chunlin Yuan, Shuman Wang, Yue Liu and Jenny Weichen Ma

This paper explores the driving factors of parasocial relationship (PSR) in the virtual reality (VR) shopping environment, and how this relationship affects brand equity. The…

2272

Abstract

Purpose

This paper explores the driving factors of parasocial relationship (PSR) in the virtual reality (VR) shopping environment, and how this relationship affects brand equity. The study also investigates the moderating role of the celebrity endorser dynamism (CED) in the relationship between PSR and its antecedents.

Design/methodology/approach

The primary data collection tool is a survey administered to Chinese consumers (n = 531) who have experienced the products of UNIQLO brand on Taobao Buy + platform, and who had a PSR with the endorser in their VR shopping process. Structural equation modeling is employed to examine the hypothesized relationships among all variables.

Findings

The findings show that VR shopping factors (i.e. physical attractiveness, social presence and technology novelty) perceived by consumers to affect PSR, and this relationship and brand equity are positively associated, while CED moderates the relationship between PSR and its antecedents.

Originality/value

This study sheds light on how PSR in the VR shopping environment can improve brand equity. It contributes to the theory of PSR and persuasion as well as marketing strategies. From a managerial perspective, guidelines are provided for firms to implement value communication activities using VR, and to increase their brand equity.

Details

Asia Pacific Journal of Marketing and Logistics, vol. 35 no. 2
Type: Research Article
ISSN: 1355-5855

Keywords

Access Restricted. View access options
Article
Publication date: 13 February 2019

Sumukh Hungund and Venkatesh Mani

The purpose of this paper is to investigate the factors influencing small and medium enterprises’ (SMEs) adoption of innovation approaches.

791

Abstract

Purpose

The purpose of this paper is to investigate the factors influencing small and medium enterprises’ (SMEs) adoption of innovation approaches.

Design/methodology/approach

The methodology involves two steps. First, all the variables relevant to the adoption of innovation in SMEs are identified. Subsequently, primary data are gathered from decision makers of 213 SMEs, and a multinomial logistic regression analysis is performed.

Findings

The results indicate that SMEs adopt both open innovation and closed innovation approaches. The firm-level factors such as firm age, firm size, education qualification, work experience and culture, and external factors such as customers, competition, technological advances and ecosystem influence adoption of open innovation approach compared to closed innovation approach. Factors such as culture among firm-level factors and competition among external factors influence the adoption of closed innovation approach.

Practical implications

The study helps the managers or the decision makers of the SMEs to know the suitable factors influencing the firm to adopt innovation which could potentially help the firms in their business strategy.

Originality/value

The study explores the adoption of innovation approaches of SMEs in emerging economies. The outcomes of this research have far-reaching implications for theory and practitioners in emerging economies.

Details

Benchmarking: An International Journal, vol. 26 no. 5
Type: Research Article
ISSN: 1463-5771

Keywords

1 – 9 of 9
Per page
102050