Search results

1 – 10 of over 3000
Per page
102050
Citations:
Loading...
Access Restricted. View access options
Article
Publication date: 29 October 2024

Huiling Yu, Sijia Dai, Shen Shi and Yizhuo Zhang

The abnormal behaviors of staff at petroleum stations pose significant safety hazards. Addressing the challenges of high parameter counts, lengthy training periods and low…

9

Abstract

Purpose

The abnormal behaviors of staff at petroleum stations pose significant safety hazards. Addressing the challenges of high parameter counts, lengthy training periods and low recognition rates in existing 3D ResNet behavior recognition models, this paper proposes GTB-ResNet, a network designed to detect abnormal behaviors in petroleum station staff.

Design/methodology/approach

Firstly, to mitigate the issues of excessive parameters and computational complexity in 3D ResNet, a lightweight residual convolution module called the Ghost residual module (GhostNet) is introduced in the feature extraction network. Ghost convolution replaces standard convolution, reducing model parameters while preserving multi-scale feature extraction capabilities. Secondly, to enhance the model's focus on salient features amidst wide surveillance ranges and small target objects, the triplet attention mechanism module is integrated to facilitate spatial and channel information interaction. Lastly, to address the challenge of short time-series features leading to misjudgments in similar actions, a bidirectional gated recurrent network is added to the feature extraction backbone network. This ensures the extraction of key long time-series features, thereby improving feature extraction accuracy.

Findings

The experimental setup encompasses four behavior types: illegal phone answering, smoking, falling (abnormal) and touching the face (normal), comprising a total of 892 videos. Experimental results showcase GTB-ResNet achieving a recognition accuracy of 96.7% with a model parameter count of 4.46 M and a computational complexity of 3.898 G. This represents a 4.4% improvement over 3D ResNet, with reductions of 90.4% in parameters and 61.5% in computational complexity.

Originality/value

Specifically designed for edge devices in oil stations, the 3D ResNet network is tailored for real-time action prediction. To address the challenges posed by the large number of parameters in 3D ResNet networks and the difficulties in deployment on edge devices, a lightweight residual module based on ghost convolution is developed. Additionally, to tackle the issue of low detection accuracy of behaviors amidst the noisy environment of petroleum stations, a triple attention mechanism is introduced during feature extraction to enhance focus on salient features. Moreover, to overcome the potential for misjudgments arising from the similarity of actions, a Bi-GRU model is introduced to enhance the extraction of key long-term features.

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: 29 August 2024

Yizhuo Zhang, Yunfei Zhang, Huiling Yu and Shen Shi

The anomaly detection task for oil and gas pipelines based on acoustic signals faces issues such as background noise coverage, lack of effective features, and small sample sizes…

35

Abstract

Purpose

The anomaly detection task for oil and gas pipelines based on acoustic signals faces issues such as background noise coverage, lack of effective features, and small sample sizes, resulting in low fault identification accuracy and slow efficiency. The purpose of this paper is to study an accurate and efficient method of pipeline anomaly detection.

Design/methodology/approach

First, to address the impact of background noise on the accuracy of anomaly signals, the adaptive multi-threshold center frequency variational mode decomposition method(AMTCF-VMD) method is used to eliminate strong noise in pipeline signals. Secondly, to address the strong data dependency and loss of local features in the Swin Transformer network, a Hybrid Pyramid ConvNet network with an Agent Attention mechanism is proposed. This compensates for the limitations of CNN’s receptive field and enhances the Swin Transformer’s global contextual feature representation capabilities. Thirdly, to address the sparsity and imbalance of anomaly samples, the SpecAugment and Scaper methods are integrated to enhance the model’s generalization ability.

Findings

In the pipeline anomaly audio and environmental datasets such as ESC-50, the AMTCF-VMD method shows more significant denoising effects compared to wavelet packet decomposition and EMD methods. Additionally, the model achieved 98.7% accuracy on the preprocessed anomaly audio dataset and 99.0% on the ESC-50 dataset.

Originality/value

This paper innovatively proposes and combines the AMTCF-VMD preprocessing method with the Agent-SwinPyramidNet model, addressing noise interference and low accuracy issues in pipeline anomaly detection, and providing strong support for oil and gas pipeline anomaly recognition tasks in high-noise environments.

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: 20 November 2017

Shi Shen, Nikita Murzintcev, Changqing Song and Changxiu Cheng

The purpose of this study is to propose a method to retrieve data on an event based on a preliminary collection of event-specific hashtags.

781

Abstract

Purpose

The purpose of this study is to propose a method to retrieve data on an event based on a preliminary collection of event-specific hashtags.

Design/methodology/approach

Extra knowledge, or a list of events with recorded features that can be used to characterize an event and separate it from other simultaneously occurring social phenomena, is employed. The first step involves the estimation and use of the impact area to retrieve messages from Twitter. This is followed by an extraction of hashtags from these messages. After that, the noisy hashtags would be filtered out by some heuristic rules. Finally, hashtags are used to collect relevant messages from not only Twitter but also other social media platforms.

Findings

The proposed method has high selectivity and is able to collect distinct sets of hashtags even for similar simultaneous events. In addition, spatial and temporal features are sufficient to improve collecting information of disaster events.

Originality/value

This work discusses a method of information retrieval of an event from cross-platform social media. The proposed method can be applied to other studies of geographically related events.

Details

Information Discovery and Delivery, vol. 45 no. 4
Type: Research Article
ISSN: 2398-6247

Keywords

Access Restricted. View access options
Article
Publication date: 14 January 2020

Shengyang Sun, Chao Zhang and Ruifa Hu

The negative externalities of pesticide overuse increasingly concern the public. However, little empirical evidence has been provided for pesticide overuse and the relationship…

496

Abstract

Purpose

The negative externalities of pesticide overuse increasingly concern the public. However, little empirical evidence has been provided for pesticide overuse and the relationship between the governmental agricultural extension system reforms and pesticide use in grain production from a nationwide perspective. The purpose of this paper is to estimate the productive effect and overuse of pesticides, and it also investigates the effect of the governmental agricultural extension system reforms on pesticide expenditure in rice, maize and wheat production in China.

Design/methodology/approach

A two-equation system model consisting of an exponential-specific damage-control production function and a pesticide use function is applied to the provincial-level data during the period 1985–2016.

Findings

While pesticide expenditure significantly increases grain productivity, the actual pesticide expenditure exceeds the economically optimal level. The commercialization reform of the governmental agricultural extension system contributed to the increase in pesticide expenditure. Moreover, the de-commercialization reform of the governmental agricultural extension system plays a limited role in pesticide reduction. Price fluctuations for grain and pesticide also impose significant effects on pesticide expenditure.

Originality/value

This study has two important policy implications for pesticide reduction in China. It is urgent to specify the functions of the governmental agricultural extension system, and encourage the development of the socialized agricultural technology service. More efforts should also be made to remove the bureaucratic intervention on the pricing mechanism of grain product and pesticide.

Details

China Agricultural Economic Review, vol. 12 no. 2
Type: Research Article
ISSN: 1756-137X

Keywords

Access Restricted. View access options
Article
Publication date: 10 May 2013

Hongyan Shi and Hui Li

The purpose of this paper is to present a clear picture of the challenges of micro drill bit and the developments of novel micro‐drill bits for flexible circuit boards…

500

Abstract

Purpose

The purpose of this paper is to present a clear picture of the challenges of micro drill bit and the developments of novel micro‐drill bits for flexible circuit boards, environmental‐friendly printed circuit boards (PCBs), high aspect ratio drill bit and ultra‐small micro drill bit, as well as the developments of geometry design of micro drill bit.

Design/methodology/approach

The paper details the developments trend and challenges of micro drill and PCBs first. Then the current research status of novel micro drill bits for flexible circuit boards, environmental‐friendly PCBs, high aspect ratio drill bit, ultra‐small micro drill bit are described. Finally, the developments of geometry design and drilling process are reviewed.

Findings

To achieve excellent performance for drilling flexible PCB, a large helical angle, large flute/land ratio and small web thickness that guarantee the sharp evacuation capability, are adopted in drill bit design. A small helix angle and an appropriate primary face angle are employed for drill bit to process environmental‐friendly printed circuit boards. It is beneficial to implement big helix angle, small primary face angles and small point angles in the design of ultra‐small micro drill bit. An optimum web thickness and step feed should be taken into consideration in high aspect ratio drill bits design.

Originality/value

The paper reviews different solutions of micro drill bits for the state‐of‐the‐art PCB and the developments of geometry design of drill bit for printed circuit boards.

Access Restricted. View access options
Article
Publication date: 14 June 2011

William Cooke, Rachel Anne Tomlinson, Richard Burguete, Daniel Johns and Gaëlle Vanard

The purpose of this paper is to rigorously determine the tensile properties of a selective laser sintering (SLS) material. Emphasis was placed on the anisotropy and inhomogeneity…

1459

Abstract

Purpose

The purpose of this paper is to rigorously determine the tensile properties of a selective laser sintering (SLS) material. Emphasis was placed on the anisotropy and inhomogeneity of the material, the repeatability of the SLS process, and the effect of age (actually moisture absorption) on the material properties.

Design/methodology/approach

Two builds of 144 dogbone tensile specimens each were tested, with 18 specimens stored for 43 days in a non‐desiccated environment before testing. Specimens were distributed throughout the build volume and aligned with the apparatus' principal axes. Tensile properties were treated statistically, using the t‐test to determine the differences between various samples.

Findings

The material was transversely isotropic in Young's modulus and strain to failure, and generally orthotropic in ultimate tensile strength. The material was inhomogeneous throughout the build volume and affected by age, with a 57 per cent reduction in University of Technology after 43 days (the changes in properties were suggested to be due to moisture absorption). Properties varied by up to 25 per cent from build‐to‐build with no change in nominal process parameters.

Research limitations/implications

It was not possible to confirm the “ageing” effect was caused by moisture absorption, and further work is suggested in this area. The causes of inhomogeneity and the effect of re‐coater action should also be studied further.

Originality/value

This is the most complete study of an SLS material's mechanical properties to date. The statistical analyses used further allow increased confidence in the conclusions drawn. This is also the only study to use cross‐fill scanning to produce specimens, and, therefore, isolate the effect of the re‐coater action.

Details

Rapid Prototyping Journal, vol. 17 no. 4
Type: Research Article
ISSN: 1355-2546

Keywords

Access Restricted. View access options
Article
Publication date: 8 June 2022

Ye Chen, Lei Shen, Xi Zhang and Yutao Chen

The purpose of this paper is twofold: first, to present a bibliometric analysis and systematic literature review of industry convergence and value innovation to understand the…

439

Abstract

Purpose

The purpose of this paper is twofold: first, to present a bibliometric analysis and systematic literature review of industry convergence and value innovation to understand the current research status; second, to provide a coherent theoretical research framework for future research.

Design/methodology/approach

This study adopts a two-step analysis approach by combining bibliometric analysis and systematic literature review to explore the research topic of industry convergence and value innovation. Besides, two bibliometric tools, HistCite and VOSviewer, were applied to this study.

Findings

This study found that Stefanie Bröring and Fredrik Hacklin are the top two most influential authors among all authors in the sample publications. Technological Forecasting and Social Change is one of the top-ranking journal that often publishes this topic of articles. Germany and the University of Munster are the most influential country and institutions, respectively. Besides, five core research themes were identified based on keywords co-occurrence map, theoretical lenses, factors promoting industry convergence, indicators of industry convergence, the impact of industry convergence and emerging research directions. Based on the above analysis, this paper constructed a theoretical research framework of industry convergence and value innovation.

Research limitations/implications

This paper only draw data from one database – Web of Science – which cannot provide broad coverage of the research topic. Besides, the bibliometric method of this paper is based on high local citation score and high-frequency words, articles in the skirting subjects’ area may not be analyzed.

Practical implications

With the rapid development of technology, such as nanotechnology, radio - frequency identification (RFID), etc., the iterative upgrading of products also comes. As a result, the boundary between industries is gradually blurred, and the phenomenon of industry convergence appears. Therefore, managerial decision-makers are facing challenges of how to respond to the convergence phenomena. From the firm level, firms are facing the problem of value innovation of the existing product, new product development and core competence improvement. Industries are facing the problem of transformation and upgrading. This paper provides certain theoretical insights for both firms and industries to guide the practice accordingly.

Originality/value

This paper is the first to use a bibliometric method to examine the topic of industry convergence and value innovation. In addition, this paper presents an in-depth analysis of this topic and provides a comprehensive theoretical research framework for future study.

Details

Kybernetes, vol. 52 no. 10
Type: Research Article
ISSN: 0368-492X

Keywords

Access Restricted. View access options
Article
Publication date: 27 May 2014

Behrooz Keshtegar and Mahmoud Miri

Generally, iterative methods which have some instability solutions in complex structural and non-linear mechanical problems are used to compute reliability index. The purpose of…

366

Abstract

Purpose

Generally, iterative methods which have some instability solutions in complex structural and non-linear mechanical problems are used to compute reliability index. The purpose of this paper is to establish a non-linear conjugate gradient (NCG) optimization algorithm to overcome instability solution of the Hasofer-Lind and Rackwitz-Fiessler (HL-RF) method in first-order reliability analysis. The NCG algorithms such as the Conjugate-Descent (CD) and the Liu-Storey (LS) are used for determining the safety index. An algorithm is found based on the new line search in the reliability analysis.

Design/methodology/approach

In the proposed line search for calculating the safety index, search direction is computed by using the conjugate gradient approach and the HL-RF method based on the new and pervious gradient vector of the reliability function. A simple step size is presented for the line search in the proposed algorithm, which is formulated by the Wolfe conditions based on the new and previous safety index results in the reliability analysis.

Findings

From the current work, it is concluded that the proposed NCG algorithm has more efficient, robust and appropriate convergence in comparison with the HL-RF method. The proposed methods can eliminate numerical instabilities of the HL-RF iterative algorithm in highly non-linear performance function and complicated structural limit state function. The NGC optimization is applicable to reliability analysis and it is correctly converged on the reliability index. In the NCG method, the CD algorithm is slightly more efficient than the LS algorithm.

Originality/value

This paper usefully shows how the HL-RF algorithm and the NCG scheme are formulated in first-order reliability analysis. The proposed algorithm is validated from six numerical and structural examples taken from the literature. The HL-RF method is not converged on several non-linear mathematic and complex structural examples, while the two proposed conjugate gradient methods are appropriately converged for all examples. The CD algorithm is converged about twice faster than the LS algorithm in most of the problems. Therefore, application of the NCG method is possible in reliability analysis.

Details

Engineering Computations, vol. 31 no. 4
Type: Research Article
ISSN: 0264-4401

Keywords

Access Restricted. View access options
Article
Publication date: 17 November 2021

Bo Fang, Panpan Zhang and Sehoon Kim

The purpose of this paper is to explore recent national human resource development (NHRD) practices in China through a literature review focusing on programs and activities that…

689

Abstract

Purpose

The purpose of this paper is to explore recent national human resource development (NHRD) practices in China through a literature review focusing on programs and activities that represent the roles and interactions among the government, industry and universities.

Design/methodology/approach

To effectively consolidate previous work and conceptualize the recent development of the NHRD practices in China, a semi-narrative literature review was used to explore and analyze NHRD-related functions and activities.

Findings

Findings from the literature review showed that although the central government still plays a predominant role in China, universities and corporations are increasingly playing a critical role in developing an innovative and skilled workforce. At the regional level, NHRD initiatives in China have been increasingly undertaken by universities, industry and government–industry–university collaborations. The authors also found a disparity between developed and underdeveloped regions in terms of NHRD in China.

Research limitations/implications

This study used the triple helix model as a framework that provides an insightful lens for researchers to examine how various social entities interact with each other and jointly contribute to NHRD. Further case studies are needed to generate evidence-based knowledge to the NHRD literature.

Practical implications

A more systematic NHRD leadership structure at both the national and local level is desired to unleash the potential of bottom-up development and active government–industry–university collaboration. To counter regional divergence in NHRD in China, intra- and cross-regional collaborations are helpful in improving resources distribution and workforce development.

Originality/value

Based on open system theory, this study focused on programs and activities that represent the roles and interactions among the government, industry and university in Chinese NHRD through the lens of the triple helix model. In addition, this study offers a conceptual model of Chinese NHRD to help scholars and practitioners understand the transitional efforts in NHRD.

Details

European Journal of Training and Development, vol. 47 no. 1/2
Type: Research Article
ISSN: 2046-9012

Keywords

Access Restricted. View access options
Article
Publication date: 30 December 2021

Sifeng Liu

The purpose of this paper is to construct some negative grey relational analysis models to measure the relationship between reverse sequences.

347

Abstract

Purpose

The purpose of this paper is to construct some negative grey relational analysis models to measure the relationship between reverse sequences.

Design/methodology/approach

The definition of reverse sequence has been given at first based on analysis of relative position and change trend of sequences. Then, several different negative grey relational analysis models, such as the negative grey similarity relational analysis model, the negative grey absolute relational analysis model, the negative grey relative relational analysis model, the negative grey comprehensive relational analysis model and the negative Deng’s grey relational analysis model have been put forward based on the corresponding common grey relational analysis models. The properties of the new models have been studied.

Findings

The negative grey relational analysis models proposed in this paper can solve the problem of relationship measurement of reverse sequences effectively. All the new negative grey relational degree satisfying the requirements of normalization and reversibility.

Practical implications

The proposed negative grey relational analysis models can be used to measure the relationship between reverse sequences. As a living example, the reverse incentive effect of winning Fields Medal on the research output of winners is measured based on the research output data of the medalists and the contenders using the proposed negative grey relational analysis model.

Originality/value

The definition of reverse sequence and the negative grey similarity relational analysis model, the negative grey absolute relational analysis model, the negative grey relative relational analysis model, the negative grey comprehensive relational analysis model and the negative Deng’s grey relational analysis model are first proposed in this paper.

1 – 10 of over 3000
Per page
102050