Search results

1 – 10 of 11
Article
Publication date: 7 March 2023

Preeti Godabole and Girish Bhole

The main purpose of the paper is timing analysis of mixed critical applications on the multicore system to identify an efficient task scheduling mechanism to achieve three main…

Abstract

Purpose

The main purpose of the paper is timing analysis of mixed critical applications on the multicore system to identify an efficient task scheduling mechanism to achieve three main objectives improving schedulability, achieving reliability and minimizing the number of cores used. The rise in transient faults in embedded systems due to the use of low-cost processors has led to the use of fault-tolerant scheduling and mapping techniques.

Design/methodology/approach

The paper opted for a simulation-based study. The simulation of mixed critical applications, like air traffic control systems and synthetic workloads, is carried out using a litmus-real time testbed on an Ubuntu machine. The heuristic algorithms for task allocation based on utilization factors and task criticalities are proposed for partitioned approaches with multiple objectives.

Findings

Both partitioned earliest deadline first (EDF) with the utilization-based heuristic and EDF-virtual deadline (VD) with a criticality-based heuristic for allocation works well, as it schedules the air traffic system with a 98% success ratio (SR) using only three processor cores with transient faults being handled by the active backup of the tasks. With synthetic task loads, the proposed criticality-based heuristic works well with EDF-VD, as the SR is 94%. The validation of the proposed heuristic is done with a global and partitioned approach of scheduling, considering active backups to make the system reliable. There is an improvement in SR by 11% as compared to the global approach and a 17% improvement in comparison with the partitioned fixed-priority approach with only three processor cores being used.

Research limitations/implications

The simulations of mixed critical tasks are carried out on a real-time kernel based on Linux and are generalizable in Linux-based environments.

Practical implications

The rise in transient faults in embedded systems due to the use of low-cost processors has led to the use of fault-tolerant scheduling and mapping techniques.

Originality/value

This paper fulfills an identified need to have multi-objective task scheduling in a mixed critical system. The timing analysis helps to identify performance risks and assess alternative architectures used to achieve reliability in terms of transient faults.

Details

International Journal of Pervasive Computing and Communications, vol. 20 no. 1
Type: Research Article
ISSN: 1742-7371

Keywords

Article
Publication date: 29 December 2023

Thanh-Nghi Do and Minh-Thu Tran-Nguyen

This study aims to propose novel edge device-tailored federated learning algorithms of local classifiers (stochastic gradient descent, support vector machines), namely, FL-lSGD…

Abstract

Purpose

This study aims to propose novel edge device-tailored federated learning algorithms of local classifiers (stochastic gradient descent, support vector machines), namely, FL-lSGD and FL-lSVM. These algorithms are designed to address the challenge of large-scale ImageNet classification.

Design/methodology/approach

The authors’ FL-lSGD and FL-lSVM trains in a parallel and incremental manner to build an ensemble local classifier on Raspberry Pis without requiring data exchange. The algorithms load small data blocks of the local training subset stored on the Raspberry Pi sequentially to train the local classifiers. The data block is split into k partitions using the k-means algorithm, and models are trained in parallel on each data partition to enable local data classification.

Findings

Empirical test results on the ImageNet data set show that the authors’ FL-lSGD and FL-lSVM algorithms with 4 Raspberry Pis (Quad core Cortex-A72, ARM v8, 64-bit SoC @ 1.5GHz, 4GB RAM) are faster than the state-of-the-art LIBLINEAR algorithm run on a PC (Intel(R) Core i7-4790 CPU, 3.6 GHz, 4 cores, 32GB RAM).

Originality/value

Efficiently addressing the challenge of large-scale ImageNet classification, the authors’ novel federated learning algorithms of local classifiers have been tailored to work on the Raspberry Pi. These algorithms can handle 1,281,167 images and 1,000 classes effectively.

Details

International Journal of Web Information Systems, vol. 20 no. 1
Type: Research Article
ISSN: 1744-0084

Keywords

Article
Publication date: 6 September 2023

Antonio Llanes, Baldomero Imbernón Tudela, Manuel Curado and Jesús Soto

The authors will review the main concepts of graphs, present the implemented algorithm, as well as explain the different techniques applied to the graph, to achieve an efficient…

Abstract

Purpose

The authors will review the main concepts of graphs, present the implemented algorithm, as well as explain the different techniques applied to the graph, to achieve an efficient execution of the algorithm, both in terms of the use of multiple cores that the authors have available today, and the use of massive data parallelism through the parallelization of the algorithm, bringing the graph closer to the execution through CUDA on GPUs.

Design/methodology/approach

In this work, the authors approach the graphs isomorphism problem, approaching this problem from a point of view very little worked during all this time, the application of parallelism and the high-performance computing (HPC) techniques to the detection of isomorphism between graphs.

Findings

Results obtained give compelling reasons to ensure that more in-depth studies on the HPC techniques should be applied in these fields, since gains of up to 722x speedup are achieved in the most favorable scenarios, maintaining an average performance speedup of 454x.

Originality/value

The paper is new and original.

Details

Engineering Computations, vol. 40 no. 7/8
Type: Research Article
ISSN: 0264-4401

Keywords

Open Access
Article
Publication date: 19 December 2023

Qinxu Ding, Ding Ding, Yue Wang, Chong Guan and Bosheng Ding

The rapid rise of large language models (LLMs) has propelled them to the forefront of applications in natural language processing (NLP). This paper aims to present a comprehensive…

1041

Abstract

Purpose

The rapid rise of large language models (LLMs) has propelled them to the forefront of applications in natural language processing (NLP). This paper aims to present a comprehensive examination of the research landscape in LLMs, providing an overview of the prevailing themes and topics within this dynamic domain.

Design/methodology/approach

Drawing from an extensive corpus of 198 records published between 1996 to 2023 from the relevant academic database encompassing journal articles, books, book chapters, conference papers and selected working papers, this study delves deep into the multifaceted world of LLM research. In this study, the authors employed the BERTopic algorithm, a recent advancement in topic modeling, to conduct a comprehensive analysis of the data after it had been meticulously cleaned and preprocessed. BERTopic leverages the power of transformer-based language models like bidirectional encoder representations from transformers (BERT) to generate more meaningful and coherent topics. This approach facilitates the identification of hidden patterns within the data, enabling authors to uncover valuable insights that might otherwise have remained obscure. The analysis revealed four distinct clusters of topics in LLM research: “language and NLP”, “education and teaching”, “clinical and medical applications” and “speech and recognition techniques”. Each cluster embodies a unique aspect of LLM application and showcases the breadth of possibilities that LLM technology has to offer. In addition to presenting the research findings, this paper identifies key challenges and opportunities in the realm of LLMs. It underscores the necessity for further investigation in specific areas, including the paramount importance of addressing potential biases, transparency and explainability, data privacy and security, and responsible deployment of LLM technology.

Findings

The analysis revealed four distinct clusters of topics in LLM research: “language and NLP”, “education and teaching”, “clinical and medical applications” and “speech and recognition techniques”. Each cluster embodies a unique aspect of LLM application and showcases the breadth of possibilities that LLM technology has to offer. In addition to presenting the research findings, this paper identifies key challenges and opportunities in the realm of LLMs. It underscores the necessity for further investigation in specific areas, including the paramount importance of addressing potential biases, transparency and explainability, data privacy and security, and responsible deployment of LLM technology.

Practical implications

This classification offers practical guidance for researchers, developers, educators, and policymakers to focus efforts and resources. The study underscores the importance of addressing challenges in LLMs, including potential biases, transparency, data privacy, and responsible deployment. Policymakers can utilize this information to shape regulations, while developers can tailor technology development based on the diverse applications identified. The findings also emphasize the need for interdisciplinary collaboration and highlight ethical considerations, providing a roadmap for navigating the complex landscape of LLM research and applications.

Originality/value

This study stands out as the first to examine the evolution of LLMs across such a long time frame and across such diversified disciplines. It provides a unique perspective on the key areas of LLM research, highlighting the breadth and depth of LLM’s evolution.

Details

Journal of Electronic Business & Digital Economics, vol. 3 no. 1
Type: Research Article
ISSN: 2754-4214

Keywords

Article
Publication date: 7 September 2023

Ibrahim A. Amar, Aeshah Alzarouq, Wajdan Mohammed, Mengfei Zhang and Noarhan Matroed

This study aims to explore the possibility of using magnetic biochar composite (MBCC) derived from Heglig tree bark (HTB) powder (agricultural solid waste) and cobalt ferrite (CoFe…

Abstract

Purpose

This study aims to explore the possibility of using magnetic biochar composite (MBCC) derived from Heglig tree bark (HTB) powder (agricultural solid waste) and cobalt ferrite (CoFe2O4, CFO) for oil spill removal from seawater surface.

Design/methodology/approach

One-pot co-precipitation route was used to synthesize MBCC. The prepared materials were characterized by X-ray diffraction, scanning electron microscopy-energy dispersive X-ray spectroscopy, Fourier transform infrared spectroscopy. The densities of the prepared materials were also estimated. Crude, diesel engine and gasoline engine oils were used as seawater pollutant models. The gravimetric oil removal (GOR) method was used for removing oil spills from seawater using MBCC as a sorbent material.

Findings

The obtained results revealed that the prepared materials (CFO and MBCC) were able to remove the crude oil and its derivatives from the seawater surface. Besides, when the absorbent amount was 0.01 g, the highest GOR values for crude oil (31.96 ± 1.02 g/g) and diesel engine oil (14.83 ± 0.83 g/g) were obtained using MBCC as an absorbent. For gasoline engine oil, the highest GOR (27.84 ± 0.46 g/g) was attained when CFO was used as an absorbent.

Originality/value

Oil spill removal using MBCC derived from cobalt ferrite and HTB. Using tree bark as biomass (eco-friendly, readily available and low-cost) for magnetic biochar preparation also is a promising method for minimizing agricultural solid wastes (e.g. HTB) and obtaining value-added-products.

Details

World Journal of Engineering, vol. ahead-of-print no. ahead-of-print
Type: Research Article
ISSN: 1708-5284

Keywords

Article
Publication date: 5 June 2023

Basil C. Sunny, Shajulin Benedict and Rajan M.P.

This paper aims to develop an architecture for 3D printers in an Industrial Internet of Things (IIoT) controlled automated manufacturing environment. An algorithm is proposed to…

Abstract

Purpose

This paper aims to develop an architecture for 3D printers in an Industrial Internet of Things (IIoT) controlled automated manufacturing environment. An algorithm is proposed to estimate the electrical energy consumption of 3D printing jobs, which is used, 3D Printing, Sustainable Manufacturing, Industry 4.0, Electrical Energy Estimation, IIoT to schedule printing jobs on optimal electrical tariff rates.

Design/methodology/approach

An IIoT-enabled architecture with connected pools of 3D printers and an Electrical Energy Estimation System (EEES) are used to estimate the electrical energy requirement of 3D printing jobs. EEES applied the combination of Maximum Likelihood Estimation and a dynamic programming–based algorithm for estimating the electrical energy consumption of 3D printing jobs.

Findings

The proposed algorithm decently estimates the electrical energy required for 3D printing and able to obtain optimal accuracy measures. Experiment results show that the electrical energy usage pattern can be reconstructed with the EEES. It is observed that EEES architecture reduces the peak power demand by scheduling the manufacturing process on low electrical tariff rates.

Practical implications

Proposed algorithm is validated with limited number of experiments.

Originality/value

IIoT with 3D printers in large numbers is the future technology for the automated manufacturing process where controlling, monitoring and analyzing such mass numbers becomes a challenging task. This paper fulfills the need of an architecture for industries to effectively use 3D printers as the main manufacturing tool with the help of IoT. The electrical estimation algorithm helps to schedule manufacturing processes with right electrical tariff.

Details

Rapid Prototyping Journal, vol. 29 no. 8
Type: Research Article
ISSN: 1355-2546

Keywords

Article
Publication date: 2 January 2023

Deepak Choudhary

As the number of devices that connect to the Internet of Things (IoT) has grown, privacy and security issues have come up. Because IoT devices collect so much sensitive…

Abstract

Purpose

As the number of devices that connect to the Internet of Things (IoT) has grown, privacy and security issues have come up. Because IoT devices collect so much sensitive information, like user names, locations, phone numbers and even how they usually use energy, it is very important to protect users' privacy and security. IoT technology will be hard to use on the client side because IoT-enabled devices do not have clear privacy and security controls.

Design/methodology/approach

IoT technology would be harder to use on the client side if the IoT did not offer enough well-defined ways to protect users’ privacy and security. The goal of this research is to protect people's privacy in the IoT by using the oppositional artificial flora optimization (EGPKC-OAFA) algorithm to generate the best keys for the ElGamal public key cryptosystem (EGPKC). The EGPKC-OAFA approach puts the most weight on the IEEE 802.15.4 standard for MAC, which is the most important part of the standard. The security field is part of the MAC header of this standard. In addition, the MAC header includes EGPKC, which makes it possible to make authentication keys as quickly as possible.

Findings

With the proliferation of IoT devices, privacy and security have become major concerns in the academic world. Security and privacy are of the utmost importance due to the large amount of personally identifiable information acquired by IoT devices, such as name, location, phone numbers and energy use. Client-side deployment of IoT technologies will be hampered by the absence of well-defined privacy and security solutions afforded by the IoT. The purpose of this research is to present the EGPKC with optimum key generation using the EGPKC-OAFA algorithm for the purpose of protecting individual privacy within the context of the IoT. The EGPKC-OAFA approach is concerned with the MAC standard defined by the IEEE 802.15.4 standard, which includes the security field in its MAC header. Also, the MAC header incorporates EGPKC, which enables the fastest possible authentication key generation. In addition, the best methodology award goes to the OAFA strategy, which successfully implements the optimum EGPKC selection strategy by combining opposition-based (OBL) and standard AFA ideas. The EGPKC-OAFA method has been proved to effectively analyze performance in a number of simulations, with the results of various functions being identified.

Originality/value

In light of the growing prevalence of the IoT, an increasing number of people are becoming anxious about the protection and confidentiality of the personal data that they save online. This is especially true in light of the fact that more and more things are becoming connected to the internet. The IoT is capable of gathering personally identifiable information such as names, addresses and phone numbers, as well as the quantity of energy that is used. It will be challenging for customers to adopt IoT technology because of worries about the security and privacy of the data generated by users. In this work, the EGPKC is paired with adversarial artificial flora, which leads in an increase to the privacy security provided by EGPKC for the IoT (EGPKC-OAFA). The MAC security field that is part of the IEEE 802.15.4 standard is one of the areas that the EGPKC-OAFA protocol places a high focus on. The Authentication Key Generation Protocol Key Agreement, also known as EGPKCA, is used in MAC headers. The abbreviation for this protocol is EGPKCA. The OAFA technique, also known as the combination of OBL and AFA, is the most successful method for selecting EGPKCs. This method is recognized by its acronym, OAFA. It has been shown via a variety of simulations that the EGPKC-OAFA technique is a very useful instrument for carrying out performance analysis.

Details

International Journal of Pervasive Computing and Communications, vol. 19 no. 5
Type: Research Article
ISSN: 1742-7371

Keywords

Article
Publication date: 6 February 2023

Bin Chen, Binsheng Xi, Nina Wan, Shuaibing Wang and Bo Tang

Because the nanocrystalline core is widely used in power electronic equipment, and the excitation waveform of its working mode is complex, the vibration at medium and high…

77

Abstract

Purpose

Because the nanocrystalline core is widely used in power electronic equipment, and the excitation waveform of its working mode is complex, the vibration at medium and high frequencies cannot be ignored. Therefore, this study aims to study the vibration mechanism of nanocrystalline strip and the vibration characteristics of nanocrystalline magnetic ring under different excitation waveforms.

Design/methodology/approach

First, the electromagnetic vibration mechanism between nanocrystalline strips is analyzed by finite element analysis, and the force of the magnetic ring with and without air gap is compared and analyzed. Then, the vibration of nanocrystalline magnetic ring under different excitation waveforms such as sine wave, triangular wave, symmetric rectangular wave and asymmetric rectangular wave is analyzed by experimental method. The acceleration time domain waveform measured by the experiment is analyzed by fast Fourier transform, and the vibration is analyzed according to the spectrum.

Findings

Because of the increase of magnetic flux leakage, the volume force density and the Maxwell force on the surface of the nanocrystalline magnetic ring will increase after the air gap is opened, resulting in the intensification of vibration. Under symmetric/asymmetric rectangular wave excitation, the vibration acceleration varies with the duty cycle. Due to the influence of harmonic excitation, the relationship between the main frequency of vibration and the excitation frequency is not two times, and its multiple decreases with the increase of excitation frequency.

Originality/value

The research and analysis of this paper can promote the application of new magnetic materials in electrical equipment in small and medium-sized and medium- to high-frequency fields.

Details

COMPEL - The international journal for computation and mathematics in electrical and electronic engineering , vol. 42 no. 3
Type: Research Article
ISSN: 0332-1649

Keywords

Article
Publication date: 6 May 2022

Mamta Mishra, Surya Prakash Singh and M. P. Gupta

The research in competitive facility location (CFL) is quite dynamic, both from a problem formulation and an algorithmic point of view. Research direction has changed immensely…

550

Abstract

Purpose

The research in competitive facility location (CFL) is quite dynamic, both from a problem formulation and an algorithmic point of view. Research direction has changed immensely over the years to address various competitive challenges. This study aims to explore CFL literature to highlight these research trends, important issues and future research opportunities.

Design/methodology/approach

This study utilises the Scopus database to search for related CFL models and adopts a five-step systematic approach for the review process. The five steps involve (1) Article Identification and keyword selection, (2) Selection criteria, (3) Literature review, (4) Literature analysis and (5) Research studies.

Findings

The paper presents a comprehensive review of CFL modelling efforts from 1981 to 2021 to provide a depth study of the research evolution in this area. The published articles are classified based on multiple characteristics, including the type of problem, type of competition, game-theoretical approaches, customer behaviour, decision space, type of demand, number of facilities, capacity and budget limitations. The review also highlights the popular problem areas and dedicated research in the respective domain. In addition, a second classification is also provided based on solution methods adopted to solve various CFL models and real-world case studies.

Originality/value

The paper covers 40 years of CFL literature from the perspective of the problem area, CFL characteristics and the solution approach. Additionally, it introduces characteristics such as capacity limit and budget constraint for the first time for classification purposes.

Details

Benchmarking: An International Journal, vol. 30 no. 4
Type: Research Article
ISSN: 1463-5771

Keywords

Article
Publication date: 20 June 2020

Alberto Sardi, Enrico Sorano, Valter Cantino and Patrizia Garengo

Current literature recognised big data as a digital revolution affecting all organisational processes. To obtain a competitive advantage from the use of big data, an efficient…

2318

Abstract

Purpose

Current literature recognised big data as a digital revolution affecting all organisational processes. To obtain a competitive advantage from the use of big data, an efficient integration in a performance measurement system (PMS) is needed, but it is still a “great challenge” in performance measurement research. This paper aims to review the big data and performance measurement studies to identify the publications’ trends and future research opportunities.

Design/methodology/approach

The authors reviewed 873 documents on big data and performance carrying out an extensive bibliometric analysis using two main techniques, i.e. performance analysis and science mapping.

Findings

Results point to a significant increase in the number of publications on big data and performance, highlighting a shortage of studies on business, management and accounting areas, and on how big data can improve performance measurement. Future research opportunities are identified. They regard the development of further research to explain how performance measurement field can effectively integrate big data into a PMS and describe the main themes related to big data in performance measurement literature.

Originality/value

This paper gives a holistic view of big data and performance measurement research through the inclusion of numerous contributions on different research streams. It also encourages further study for developing concrete tools.

Details

Measuring Business Excellence, vol. 27 no. 4
Type: Research Article
ISSN: 1368-3047

Keywords

1 – 10 of 11