Forthcoming and Online First Articles

International Journal of Intelligent Engineering Informatics

International Journal of Intelligent Engineering Informatics (IJIEI)

Forthcoming articles have been peer-reviewed and accepted for publication but are pending final changes, are not yet published and may not appear here in their final order of publication until they are assigned to issues. Therefore, the content conforms to our standards but the presentation (e.g. typesetting and proof-reading) is not necessarily up to the Inderscience standard. Additionally, titles, authors, abstracts and keywords may change before publication. Articles will not be published until the final proofs are validated by their authors.

Forthcoming articles must be purchased for the purposes of research, teaching and private study only. These articles can be cited using the expression "in press". For example: Smith, J. (in press). Article Title. Journal Title.

Articles marked with this shopping trolley icon are available for purchase - click on the icon to send an email request to purchase.

Online First articles are published online here, before they appear in a journal issue. Online First articles are fully citeable, complete with a DOI. They can be cited, read, and downloaded. Online First articles are published as Open Access (OA) articles to make the latest research available as early as possible.

Open AccessArticles marked with this Open Access icon are Online First articles. They are freely available and openly accessible to all without any restriction except the ones stated in their respective CC licenses.

Register for our alerting service, which notifies you by email when new issues are published online.

We also offer which provide timely updates of tables of contents, newly published articles and calls for papers.

International Journal of Intelligent Engineering Informatics (11 papers in press)

Regular Issues

  • MSalp-Epi: Multi-objective Salp Optimization for Epistasis detection in Genome-Wide Association Studies   Order a copy of this article
    by S. Priya, R. Manavalan 
    Abstract: Epistasis effects are depicted as interactions between different Single Nucleotide Polymorphism (SNPs). It plays an essential role to recognize the individual susceptibility to complex human diseases. In this paper, we present a two-stage approach based on Multi-objective Salp Optimization for Epistasis detection (MSalp-Epi) to detect two-locus epistasis associations for various simulated disease models. In the first stage, the Salp optimizations use AIC and K2 scores as objective functions to find the non-dominated disease-related SNPs. In the second stage, the G-test statistic is applied over the non-dominated SNPs to attain the significant SNP pairs. The main objective of MSalp-Epi is to establish rapid and efficient multi-objective salp that accelerates the identification of disease-related SNP-SNP interactions from thousands of SNPs. The performance of MSalp-Epi is analyzed and compared with MACOED and CSE. The outcome of the experimental analysis revealed that MSalp-Epi is superior to MACOED and CSE in terms of power, accuracy, True positive rate, false detection rate Specificity, positive predicted value, F1-score and running time.
    Keywords: epistasis; genetic interactions; salp optimization; multi-objective; Single Nucleotide Polymorphism (SNPs); complex diseases; GWAS; G-test; two-locus; three-locus;.

  • Lexical Semantic Analysis to Support Ontology Maintenance Modeling of Failure-Mode-Effect Analysis   Order a copy of this article
    by Vahid Ebrahimipour, Mohammad Sheikhalishahi 
    Abstract: For text-based documents, word representations and meaning extraction play essential roles in knowledge modeling and presentation. Businesses produce procedures that are written in natural language; the corresponding documents are intended to store technical and engineering information, management decisions, and operation experience during a production system life cycle. A maintenance procedure comprises consecutive logical arguments for determining step-by-step cause-effect events, ideally resulting in mitigative tasks. Therefore, the context and meaning representation when mimicking the purpose of a maintenance procedure are highly dependent on the word sense, syntax-semantic interface, and semantic features of the argument. This paper proposes an event-based ontology approach for supporting a failure-mode-effect analysis (FMEA), based on a lexical semantic analysis. The approach constructs a straightforward lexical semantic for analyzing the semantic and syntactic features of the contextual structures of maintenance reports to facilitate translation and interpretation for knowledge reasoning in the format of FMEA. The knowledge is converted into a computer-understandable representation with less heterogeneity and ambiguity. At first, it maps the argument structure into a causal event structure, in which an event is represented as a group of highly frequent contextual features or words logically linked together to shape structured arguments. Then, Valins model is employed in the format of [Event-State-Activity-Accomplishment-Result] to determine the syntax-sematic interface and linking rules in the causal chain. Finally, the metadata and/or hypernyms of causal events are represented, to accommodate ontology modeling for semantic extraction and cause-effect interpretation using Web Ontology Language (W3C).
    Keywords: Maintenance Data Modeling; Lexical Semantic Analysis; Contextual Meaning Extraction; Maintenance Knowledge Representation; Ontology Modeling.

  • A Cladistic Approach to the Evolution of Steppe Scripts   Order a copy of this article
    by Timea Puskás, Gábor Hosszú 
    Abstract: The article deals with the cladistic modelling of the evolution of specific pattern systems, namely historical scripts. A pattern system is a specific form of symbolic communication consisting of symbols and the syntactic rules that determine the symbols use. Some pattern systems have evolutionary properties; historical scripts are one such type of pattern system. The evolutionary (phylogenetic) study of pattern systems is called pattern evolution, a subfield of scriptinformatics that deals with the evolution of historical scripts. The main obstacle to phylogenetic modelling of historical scripts is the small number of features (phylogenetic characters), which means a high risk of homoplasies (identical features in several non-common ancestral taxa) that would degrade the quality of the modelling. Therefore, based on the available data, the evolution of some historical scripts cannot be analysed directly using cladistic methods that reveal evolutionary relationships but only using phenetic analysis that reveals similarity relationships. In previous research, this phenetic model was extended with evolutionary considerations. The so-called successive elimination procedure on the resulting extended phenetic model avoids homoplasies, and the resulting database is already suitable for cladistic analysis. The procedure described in this article illustrates cladistic analysis performed this way. A cladogram is generated using Wagners method, and the algorithm that determines the optimal cladograms is based on the Branch and Bound method. The procedure has been applied to the scripts of the steppe peoples, and the necessary software has been written in Python programming language.
    Keywords: cladistics; consistency index; machine learning; pattern evolution; pattern system; phenetics; retention index; Rovash scripts; scriptinformatics; Wagner method.

  • Multi-view multi-depth soil temperature prediction (MV-MD-STP): A new approach using machine learning and time series methods   Order a copy of this article
    by Goksu Tuysuzoglu, Derya Birant, Volkan Kiranoglu 
    Abstract: Estimation of soil temperature is of great importance because of its great effects on plant development, yield increase, chemical and biological activities in the soil. This paper proposes a novel multi-view multi-depth learning framework for soil temperature prediction. Under the proposed framework, soil temperature prediction at various soil depths is performed using multivariate time series and machine learning methods. This is the first study that two different views to represent antecedent soil data and past meteorological data were designed to capture different features. According to the experimental results, when Support Vector Regression is applied with the multi-view multi-depth learning framework, the predicted soil temperature values approached to the real values at most, and it outperformed other methods. It is the first time that multi-view multi-depth learning has been provided a very powerful opportunity to estimate soil temperature when both time series and machine learning methods are used as base learners.
    Keywords: machine learning; multi-view learning; multivariate time series; soil temperature prediction; agriculture.

  • On the Performance of Modified Generalised Quadrature Spatial Modulation under Correlated Weibull Fading   Order a copy of this article
    by Kiran Gunde, Anuradha Sundru 
    Abstract: To improve the data rate of ``quadrature spatial modulation (QSM)'', a ``modified generalized quadrature spatial modulation (mGQSM)'' scheme is developed. This scheme can activate more antennas to transmit the data by utilising multiple radio frequency chains. The mGQSM employs two sets of active antenna patterns (AAP), one for transmitting the real part of a selected complex data symbol and the other for transmitting the imaginary part of the same symbol. In mGQSM, the number of AAP vectors are more when compared to the generalised QSM (GQSM) for the same system configuration. This paper presents the mGQSM and ``reduced codebook mGQSM (RC-mGQSM)'' system performances over correlated Weibull fading channels under two different fading environments. For the computer simulations, we consider Weibull non-fading and deep-fading environments with the Weibull parameter values are equal to 5 and 0.5, respectively. Using maximum likelihood (ML) detector, the mGQSM and RC-mGQSM systems are compared to that of QSM and GQSM systems over uncorrelated and correlated Weibull fading channels. Also, presents the mGQSM system performance in the existence of imperfect channel knowledge and compared to that of QSM.
    Keywords: spatial modulation (SM); modified GQSM (mGQSM); correlated; Weibull fading; imperfect channel; maximum likelihood (ML) detection.

  • Knowledgeable Network-on-Chip Accelerator for Fast and Accurate simulations using Supervised Learning Algorithms and Multiprocessing   Order a copy of this article
    by Anil Kumar, Basavaraj Talawar 
    Abstract: In this paper, we propose a Network-on-Chip (NoC) accelerator using Machine Learning (ML) algorithms and multiprocessing to predict the design parameters of NoCs with a fixed and accurate delay between intellectual property (IP) starting from various traffic models of large-scale architectures for performance evaluation. For analyzing and testing new NoC architecture, designers mainly depend on simulators through which they can achieve the best performance vs. cost tradeoff which will be very beneficial for interconnect designer as well as the system designer. As the size of the NoC increases simulator consumes more time to complete simulations. To overcome this problem the proposed framework named Knowledgeable Network-on-Chip Accelerator (K-NoC) can be used to analyze various NoC architectures considering different architecture sizes, virtual channels, buffers, injection rates and traffic patterns. In this work, we explore the capability of decision tree regression (DTR) for performance prediction in two different scenarios, the fixed delay between the IPs and floorplan based (accurate) delay between the IPs of NoC. The results showed that DTR produced significant prediction accuracy for the number of predictions made in both scenarios. The outcome of K-NoC results was compared with the widely used cycle-accurate Booksim NoC simulator. It showed a minimum speedup of 12Kx when compared to Booksim and error rate was less than 6% in both scenarios.
    Keywords: Network-on-Chip; Floorplan; Performance modelling; Simulation; Machine Learning; Prediction; Regression; Decision Tree; Booksim; Performance evaluation; Power; Area; Router; Traffic Pattern.

  • Harmonics Estimator Design with Trigonometric function inspired Grey Wolf Optimizer   Order a copy of this article
    by Aishwarya Mehta, Jitesh Jangid, Akash Saxena, Shalini Shekhawat, Rajesh Kumar 
    Abstract: Modern power systems are vulnerable to power quality issues due to competitive business environment, stressed grid conditions and usage of renewable technology in generation. Power quality issues emerge as potential threats sometimes in stressed grid conditions. Addition to that, presence of harmonics in fundamental waves consider as a root cause of deterioration of equipment\'s life and performance. Moreover, the ill effect of these harmonics associated with the quality of life, mitigation of these required accurate estimation of harmonic components. More recently, some efficient approaches regarding design of mitigation technologies are with the help of metaheuristics. From taking inspiration of these, the work presented in the manuscript is a proposal of harmonic estimator design based on proposed Trigonometric Function Inspired Grey Wolf Optimizer (T-GWO). To validate performance of T-GWO we tested proposed variant on conventional bench and then a harmonic estimator design is executed. We observe and witness the satisfactory performance of T-GWO as compared with the other state of the art approaches existed in literature.
    Keywords: Wavelet Transform; Auto-Regressive Model; Grey Wolf Optimization; Chirp-Z Transform.

  • Detection of Coronavirus Disease using Texture Analysis and Machine Learning Methods   Order a copy of this article
    by Sami Bourouis 
    Abstract: The recent outbreak of the novel SARS-CoV-2 virus (COVID-19) has caused serious problems across the world. Patients with such disease can have severe symptoms and may die. The early diagnosis of COVID-19 may reduce the death rate. Chest X-ray technology is one of the good low-cost diagnostic tools in analyzing such disease. However, its accurate detection is becoming prone to serious errors caused by the low radiographic contrast. In this paper, we address the problem of data classification using texture features and machine learning along with artificial intelligence algorithms. The aim is to show that it is possible to take advantage of some well-known AI algorithms to accurately diagnose COVID-19. An evaluation process was conducted on real datasets showing the merits of these algorithms. The other aim is to show the robustness of texture features in solving the current problem. Experiments show promising results with high accuracy for most models.
    Keywords: COVID-19; X-ray images; Texture features; Image classification; Machine learning; Comparative study.
    DOI: 10.1504/IJIEI.2022.10047137

Special Issue on: ICCIS-2020 Applications of Nature Inspired Algorithms in Optimisation

  • Fully Informed ABC Algorithm for Large Scale Job Shop Scheduling problem   Order a copy of this article
    by Kavita Sharma, P.C. Gupta 
    Abstract: The large-scale job-shop scheduling problem (LSJSSP) is a complex scheduling problems. Previously, although the nature-inspired algorithm, specially the swarm intelligence (SIA) based algorithms have been efficiently applied to solve the LSJSSP, finding the best solution for LSJSSP instances remains a challenging task. Therefore, in this paper, a novel SIA is applied to solve the 105 LSJSSP instances. The selected SIA is Fully Informed Artificial Bee Colony (FABC) algorithm. The FABC algorithm is a variant of the ABC algorithm in which position update process is inspired from the GABC. In the FABC, onlooker bee process of the ABC strategy is modified and designed such that the new position of the solution search agent is obtained while learning from all the nearby agents. The results obtained by the FABC is compared with the strategies available in the literature. The results analysis shows that the proposed approach to solving LSJSSP is competitive in the field of SIA.
    Keywords: Fully Informed Learning; Swarm Intelligence; Artificial bee colony; large-scale JSS Problem.

  • Multi-Objective Tunicate Search Optimization Algorithm for Numerical Problems   Order a copy of this article
    by Isha Sharma, Vijay Kumar 
    Abstract: In this paper, a multi-objective version of recently developed Tunicate Swarm Algorithm (TSA) is proposed. The multi-objective TSA (MOTSA) utilizes the external archive to store the non-dominated solutions. The concept of roulette wheel mechanism is also incorporated in MOTSA for selection of non-dominated solutions. To demonstrate the effectiveness of MOTSA, it is evaluated on the well-known benchmark test functions. The proposed MOTSA is compared with four well-renowned multi-Objective optimization algorithms and quantitatively analysed by using the performance measures. The experimental results reveal that the proposed MOTSA outperforms the existing techniques in terms of performance measures.
    Keywords: Tunicate search optimizer; Optimization; Swarm intelligence; Multi-Objective optimization.

  • Economic load dispatch problem using spider monkey optimization algorithm   Order a copy of this article
    by Ajay Sharma, Harish Sharma, Annapurna Bhargava, Nirmala Sharma 
    Abstract: The coal reserves are lessening, and subsequently fuel prices are escalating now a days. Therefore, an appropriate schedule of generating units for thermal energy is indispensable to convince this rising load demand at minimum price by reducing generation cost is termed as economic load dispatch problem (ELDP). Spider monkey optimization algorithm (SMOA) is implied to execute ELDP. The proposed methodology considers transmission losses, prohibited operating zones, and multiple fuels constraints. The experiments were executed over a variety of arrangements of a different number of generating units. The significance of the applied strategy to solve ELDP is analyzed while assessing the reported results with other renowned methods.
    Keywords: Swarm Intelligence; Economic Load Dispatch Problem; Spider Monkey Optimization; Nature Inspired Algorithm.