Search results

1 – 10 of 10
Per page
102050
Citations:
Loading...
Access Restricted. View access options
Article
Publication date: 25 June 2019

Sławomir Opałka, Dominik Szajerman and Adam Wojciechowski

The purpose of this paper is to apply recurrent neural networks (RNNs) and more specifically long-short term memory (LSTM)-based ones for mental task classification in terms of…

118

Abstract

Purpose

The purpose of this paper is to apply recurrent neural networks (RNNs) and more specifically long-short term memory (LSTM)-based ones for mental task classification in terms of BCI systems. The authors have introduced novel LSTM-based multichannel architecture model which proved to be highly promising in other fields, yet was not used for mental tasks classification.

Design/methodology/approach

Validity of the multichannel LSTM-based solution was confronted with the results achieved by a non-multichannel state-of-the-art solutions on a well-recognized data set.

Findings

The results demonstrated evident advantage of the introduced method. The best of the provided variants outperformed most of the RNNs approaches and was comparable with the best state-of-the-art methods.

Practical implications

The approach presented in the manuscript enables more detailed investigation of the electroencephalography analysis methods, invaluable for BCI mental tasks classification.

Originality/value

The new approach to mental task classification, exploiting LSTM-based RNNs with multichannel architecture, operating on spatial features retrieving filters, has been adapted to mental tasks with noticeable results. To the best of the authors’ knowledge, such an approach was not present in the literature before.

Details

COMPEL - The international journal for computation and mathematics in electrical and electronic engineering, vol. 38 no. 4
Type: Research Article
ISSN: 0332-1649

Keywords

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

Adam Sadowski, Piotr Wojciechowski and Per Engelseth

In a volatile marketplace, warehouse management is fundamentally contingent of changes in its supply network environment. Flexibility is therefore a key logistics issue in…

790

Abstract

Purpose

In a volatile marketplace, warehouse management is fundamentally contingent of changes in its supply network environment. Flexibility is therefore a key logistics issue in distribution centre management. This study probes into the nature of warehouse flexibility in a supply network through simulation.

Design/methodology/approach

By using the FlexSim simulation tool the dynamic behaviour of the warehouse system are conceptualised, documented, simulated, analysed and evaluated.

Findings

Simulation revealed that external changes affect daily processes and the reorganisation of warehouse processes. Given the extensity of resource use, simulation also revealed that process reorganisation should not be a daily undertaking. This is because warehouse processes react in unpredictable and different manners to even the smallest disturbance from the environment. This reaction is not necessarily negative impending more long-term change of warehouse processes.

Originality/value

The warehouse is a complex system that self-adapts with limited need to calculate new optimised warehouse processes to counter changes in its environment. Rather than following deterministic optimisation procedures, the development of flexible resources is a key issue in warehouse management. The applied simulation model is generic and therefore applicable in other distribution centres pointing to how to monitor warehouse processes to in a pre-emptively develop warehouse flexibility through change of process context.

Details

International Journal of Productivity and Performance Management, vol. 71 no. 8
Type: Research Article
ISSN: 1741-0401

Keywords

Access Restricted. View access options
Article
Publication date: 29 April 2019

Adam Jakubas, Radosław Jastrzębski and Krzysztof Chwastek

The purpose of this paper is to examine the effect of varying compaction pressure on magnetic properties of self-developed soft magnetic composite (SMC) cores. The change in shape…

135

Abstract

Purpose

The purpose of this paper is to examine the effect of varying compaction pressure on magnetic properties of self-developed soft magnetic composite (SMC) cores. The change in shape of ferromagnetic hysteresis curves has – in turn – the impact on the values of hysteresis model parameters. The phenomenological GRUCAD model is chosen for description of hysteresis curves.

Design/methodology/approach

Several cylinder-shaped cores have been made from a mixture of iron powder and suspense polyvinyl chloride using a hydraulic press with a form and a band with a thermocouple for controlling heat treatment conditions. The only varying parameter in the study is the compaction pressure. The magnetic properties of developed cores have been measured using a computer-acquisition card and LabView software. The obtained hysteresis curves are fitted to the equations of the phenomenological GRUCAD model. This description is compliant with the laws of irreversible thermodynamics. The variations of model parameters are presented as functions of compacting pressure.

Findings

The compaction pressure has a significant impact on magnetic properties of self-developed SMC cores. The paper provides a number of charts useful for checking how the parameters of the hysteresis model are affected.

Research limitations/implications

The present paper is limited to modelling symmetrical loops only. Description of more complex magnetization cycles is postponed to another, forthcoming paper.

Practical implications

The GRUCAD hysteresis model may be a useful tool for the designers of magnetic circuits. Its parameters depend on the processing conditions (in this study – the compaction pressure) of the SMC cores.

Originality/value

Modelling of magnetic properties of SMC cores has been carried so far using some well-known description like Preisach, Takács and Jiles–Atherton proposals. The GRUCAD model has a number of advantages, and it may be a useful alternative to the latter formalism. So far it has been used for description of hysteresis curves in conventional materials like non-oriented and grain-oriented electrical steels. In the present work, it is applied to novel SMC materials.

Details

COMPEL - The international journal for computation and mathematics in electrical and electronic engineering, vol. 38 no. 4
Type: Research Article
ISSN: 0332-1649

Keywords

Access Restricted. View access options
Article
Publication date: 28 May 2021

Zhengtuo Wang, Yuetong Xu, Guanhua Xu, Jianzhong Fu, Jiongyan Yu and Tianyi Gu

In this work, the authors aim to provide a set of convenient methods for generating training data, and then develop a deep learning method based on point clouds to estimate the…

372

Abstract

Purpose

In this work, the authors aim to provide a set of convenient methods for generating training data, and then develop a deep learning method based on point clouds to estimate the pose of target for robot grasping.

Design/methodology/approach

This work presents a deep learning method PointSimGrasp on point clouds for robot grasping. In PointSimGrasp, a point cloud emulator is introduced to generate training data and a pose estimation algorithm, which, based on deep learning, is designed. After trained with the emulation data set, the pose estimation algorithm could estimate the pose of target.

Findings

In experiment part, an experimental platform is built, which contains a six-axis industrial robot, a binocular structured-light sensor and a base platform with adjustable inclination. A data set that contains three subsets is set up on the experimental platform. After trained with the emulation data set, the PointSimGrasp is tested on the experimental data set, and an average translation error of about 2–3 mm and an average rotation error of about 2–5 degrees are obtained.

Originality/value

The contributions are as follows: first, a deep learning method on point clouds is proposed to estimate 6D pose of target; second, a convenient training method for pose estimation algorithm is presented and a point cloud emulator is introduced to generate training data; finally, an experimental platform is built, and the PointSimGrasp is tested on the platform.

Details

Assembly Automation, vol. 41 no. 2
Type: Research Article
ISSN: 0144-5154

Keywords

Access Restricted. View access options
Book part
Publication date: 13 December 2010

Magdalena Gross

This chapter examines the processes of rewriting nationhood in educational narratives regarding the Second World War (WWII) in Poland. Using mixed methods, this case study…

Abstract

This chapter examines the processes of rewriting nationhood in educational narratives regarding the Second World War (WWII) in Poland. Using mixed methods, this case study analyzes narrative change in state-approved history textbooks published between 1977 and 2008, thus covering the period of political transition from a communist to a democratic Poland. Although trends in learning theory and international norms suggest that attention to diversity should have increased in textbooks, in Poland these trends have been subsumed by more long-lasting Polish specific cultural tropes. WWII narratives, in particular, emphasize an ethnically homogeneous nation. Throughout the 31-year sample, educating youth about WWII in Poland continues to be focused on reclaiming “Polishness” rather than on espousing global understandings and citizenship.

Details

Post-Socialism is not Dead: (Re)Reading the Global in Comparative Education
Type: Book
ISBN: 978-0-85724-418-5

Keywords

Access Restricted. View access options
Article
Publication date: 8 June 2015

Deryk Stec

This paper aims to examine how residues of ancient images have influenced one’s perspectives on management. Increased attention has been given to the absence of bodies within…

354

Abstract

Purpose

This paper aims to examine how residues of ancient images have influenced one’s perspectives on management. Increased attention has been given to the absence of bodies within discussions of organisations; however, far less attention has been given to the interplay between organisations and images of one’s body.

Design/methodology/approach

By comparing the perceived benefits of studying sport (e.g. passion, embodiment and action) with the tensions that existed between athletic performances and an ancient image of the body, this paper draws attention to residuals that exist within discussions of organisations.

Findings

In a context where an image of the body encouraged moderation, the appropriate levels of heat, and the development of an immaterial and eternal soul, athletic performances, which were physical, extreme, focused on the body and generated excessive heat, were often problematic. These problems are then examined within the literature discussing current issues in management.

Research limitations/implications

Sport has the potential to facilitate one’s understanding of issues that management, consistent with ancient images of the body, has traditionally neglected (i.e. extremes, passion) and the possibilities of using embodied cognition to enhance our understandings of performance, teams and leading are discussed.

Social implications

As scientists become increasingly concerned about the long-term consequences of the reduced opportunities for cultural programs (sport, art, music, etc.), revisiting one’s assumptions is increasingly important, especially as athletics and philosophy once shared the same physical space.

Originality/value

By describing how residues from historical images of the body have influenced the thinking about organizing, this paper highlights the connection between the social and the biological and demonstrates how vestiges from the past influence contemporary discussions.

Details

Journal of Management History, vol. 21 no. 3
Type: Research Article
ISSN: 1751-1348

Keywords

Access Restricted. View access options
Article
Publication date: 5 May 2015

Witold Mazgaj and Adam Warzecha

The purpose of this paper is to present the differences in results of numerical calculations arising from different simplifications of the rotational magnetization model in…

73

Abstract

Purpose

The purpose of this paper is to present the differences in results of numerical calculations arising from different simplifications of the rotational magnetization model in typical dynamo sheets.

Design/methodology/approach

A comprehensive model of rotational magnetization processes in typical dynamo sheets should take into consideration the magnetic hysteresis and eddy current phenomena and also certain anisotropic properties. The chosen model of the rotational magnetization is briefly presented in this paper. A method of the inclusion of the rotational magnetization model into equations of the magnetic field distribution is described. The correctness of these equations has been verified experimentally. Numerical calculations of the rotational magnetization in two types of dynamo sheets were carried out for several simplifications of the described model.

Findings

Results of numerical calculations of the rotational magnetization with the omission of the hysteresis phenomenon or with the omission of eddy currents were compared with results obtained with the use of the comprehensive model of the rotational magnetization.

Practical implications

The paper presents comments and recommendations concerning the omission of both the hysteresis phenomenon and eddy currents in the analysis of the rotational magnetization in dynamo sheets and the impact of these simplifications on numerical calculation results.

Originality/value

The content of the paper refers to very important issues of modeling and calculations of the rotational magnetization in typical dynamo steel sheets.

Details

COMPEL: The International Journal for Computation and Mathematics in Electrical and Electronic Engineering, vol. 34 no. 3
Type: Research Article
ISSN: 0332-1649

Keywords

Access Restricted. View access options
Article
Publication date: 10 August 2012

Idriss El‐Thalji and Jayantha P. Liyanage

The purpose of this paper is to review the operation and maintenance practices within wind power applications and to clarify practical needs as gaps between researchers and…

2445

Abstract

Purpose

The purpose of this paper is to review the operation and maintenance practices within wind power applications and to clarify practical needs as gaps between researchers and practitioners.

Design/methodology/approach

The paper collects, categorizes, and analyzes the published literature of both researchers and practitioners systematically.

Findings

The paper defines significant issues in operation and maintenance of wind energy related to: site and seasonal asset disturbances; stakeholders’ requirements trade‐off; dependability and asset deterioration challenges; diagnostic, prognostic and information and communication technologies (ICTs) applications; and maintenance optimization models. Within each category, the gaps and further research needs have been extracted with respect to both an academic and industrial perspective.

Practical implications

The use of wind energy is growing rapidly and the associated practices related to maintenance and asset management are still lacking. Therefore, the literature review of operation and maintenance is a necessity to uncover the holistic issues and interrelationships of what has so far been published as detailed and fragmented topics to specific issues. Wind energy assets represent modern renewable energy assets which are affected by environmental disturbances, rapid technological development, rapid scaling‐up processes, the stochastic and dynamic nature of operations and degradation, the integrity and interoperability of system‐to‐support.

Originality/value

The paper provides a comprehensive review of research contributions and industrial development efforts. That will be useful to the life cycle stakeholders in both academia and industry in understanding the maintenance problem and solution space within the wind energy context.

Access Restricted. View access options
Article
Publication date: 10 October 2016

Fazel Ansari, Madjid Fathi and Ulrich Seidenberg

The purpose of this paper is to investigate the use of problem-solving approaches in maintenance cost management (MCM). In particular, the paper aims to examine characteristics of…

1396

Abstract

Purpose

The purpose of this paper is to investigate the use of problem-solving approaches in maintenance cost management (MCM). In particular, the paper aims to examine characteristics of MCM models and to identify patterns for classification of problem-solving approaches.

Design/methodology/approach

This paper reflects an extensive and detailed literature survey of 68 (quantitative or qualitative) cost models within the scope of MCM published in the period from 1969 to 2013. The reviewed papers have been critically examined and classified based on implementing a morphological analysis which employs eight criteria and associated expressions. In addition, the survey identified two main perspectives of problem solving: first, synoptic/incremental and second, heuristics/meta-heuristics.

Findings

The literature survey revealed the patterns for classification of the MCM models, especially the characteristics of the models for problem-solving in association with the type of modeling, focus of purpose, extent and scope of application, and reaction and dynamics of parameters. Majority of the surveyed approaches is mathematical, respectively, synoptic. Incremental approaches are much less and only few are combined (i.e. synoptic and incremental). A set of features is identified for proper classification, selection, and coexistence of the two approaches.

Research limitations/implications

This paper provides a basis for further study of heuristic and meta-heuristic approaches to problem-solving. Especially the coexistence of heuristic, synoptic, and incremental approaches needs to be further investigated.

Practical implications

The detected dominance of synoptic approaches in literature – especially in the case of specific application areas – contrasts to some extent to the needs of maintenance managers in practice. Hence the findings of this paper particularly address the need for further investigation on combining problem-solving approaches for improving planning, monitoring, and controlling phases of MCM. Continuous improvement of MCM, especially problem-solving and decision-making activities, is tailored to the use of maintenance knowledge assets. In particular, maintenance management systems and processes are knowledge driven. Thus, combining problem-solving approaches with knowledge management methods is of interest, especially for continuous learning from past experiences in MCM.

Originality/value

This paper provides a unique study of 68 problem-solving approaches in MCM, based on a morphological analysis. Hence suitable criteria and their expressions are provided. The paper reveals the opportunities for further interdisciplinary research in the maintenance cost life cycle.

Details

Journal of Quality in Maintenance Engineering, vol. 22 no. 4
Type: Research Article
ISSN: 1355-2511

Keywords

Access Restricted. View access options
Article
Publication date: 28 September 2010

Ingrid Bouwer Utne

The objective of this paper is to outline a framework that guides the development of sound maintenance strategies and policies for deep‐sea offshore wind turbines.

2675

Abstract

Purpose

The objective of this paper is to outline a framework that guides the development of sound maintenance strategies and policies for deep‐sea offshore wind turbines.

Design/methodology/approach

An important challenge with offshore wind energy production is to reduce the high operation and maintenance costs. To decrease complexity, and structure the maintenance strategy developing process, systems engineering principles are used.

Findings

The framework facilitates integration of fragmented but valuable information from different disciplines in the development of sound maintenance strategies. In addition, the framework may be used to identify knowledge gaps, and areas for further research.

Research limitations/implications

The paper refers to research on deep‐sea offshore wind turbines, which is in its infancy, with a limited amount of data yet available for verification and validation. Deep‐sea offshore installations are not commercialized, and few pilot installations have been installed.

Originality/value

The design of the offshore wind turbines determines operation and maintenance features. Reducing operation and maintenance costs is necessary to make deep‐sea offshore wind projects viable in the first place. The framework contributes to the complicated development of maintenance strategies for a system not yet realized.

Details

Journal of Quality in Maintenance Engineering, vol. 16 no. 4
Type: Research Article
ISSN: 1355-2511

Keywords

1 – 10 of 10
Per page
102050