Forthcoming and Online First Articles

International Journal of Artificial Intelligence and Soft Computing

International Journal of Artificial Intelligence and Soft Computing (IJAISC)

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 Articles will not be published until the final proofs are validated by their authors.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.

International Journal of Artificial Intelligence and Soft Computing (6 papers in press)

Regular Issues

  • Application of Machine Learning in Grain-Related Clustering of Laue Spots in a Polycrystalline Energy Dispersive Laue Pattern   Order a copy of this article
    by Amir Tosson, Mohammad Shokr, Mahmoud Al Humaidi, Eduard Mikayelyan, Christian Gutt, Ulrich Pietsch 
    Abstract: We address the identification of grain-corresponding Laue reflections in energy dispersive Laue diffraction (EDLD) experiments by formulating it as a clustering problem solvable through unsupervised machine learning (ML). To achieve reliable and efficient identification of grains in a Laue pattern, we employ a combination of clustering algorithms, namely hierarchical clustering (HC) and K-means. These algorithms allow us to group together similar Laue reflections, revealing the underlying grain structure in the diffraction pattern. Additionally, we utilise the elbow method to determine the optimal number of clusters, ensuring accurate results. To evaluate the performance of our proposed method, we conducted experiments using both simulated and experimental datasets obtained from nickel wires. The simulated datasets were generated to mimic the characteristics of real-world EDLD experiments, while the experimental datasets were obtained from actual measurements.
    Keywords: machine learning; Laue diffraction; X-ray; hierarchical clustering; K-means; crystallography; artificial intelligence; synchrotron radiation; polycrystalline material.
    DOI: 10.1504/IJAISC.2024.10065524
     
  • Modelling the Profitability of Soyabean Farming in Zambia using Machine Learning   Order a copy of this article
    by Naomi M. Mwaba, Derrick Ntalasha 
    Abstract: Planning crops for any upcoming season has proven to be a tough chore for farmers since it is challenging to forecast the profits that their crops will fetch after harvest as most farmers base their choice of crop to grow on high-yield crops and previous farming season profit margins. This introduces a problem of profit determination over time. This study uses soya bean data for the past ten farming seasons to develop and compare two machine learning (ML) models using support vector machine regression (SVMR) and autoregressive integrated moving average (ARIMA) to forecast the profitability of soya beans in Zambia. The experimental results demonstrate that the SVMR is best suited as it predicted profits with an accuracy of 79.25% compared to ARIMA with an accuracy of only 34.2%. This suggests that the SVMR model is efficient to use as a financial analysis tool to allow farmers to make informed decisions.
    Keywords: profit prediction; machine learning; support vector machine regression; SVMR; autoregressive integrated moving average; ARIMA; Zambia.
    DOI: 10.1504/IJAISC.2024.10065638
     
  • License Plate Redaction Algorithm: A Privacy-Preserving Approach   Order a copy of this article
    by Divyanka Thakur, Bhagyalakshmi V, Sonali Deshpande, Sunil Chavan 
    Abstract: License plates are assigned to every vehicle for identification which displays unique letter-number combinations containing sensitive owner details. Redaction is masking of the sensitive information in media and is essential in surveillance to protect privacy. This research proposes an automated license plate redaction system using NVIDIA DeepStream. Leveraging object detection and recognition models, the system identifies and redacts license plates in realtime video footage. A dataset of various vehicles is compiled, annotated, and trained on YOLO-V5s, achieving 97% accuracy in license plate detection. Integrated with DeepStream and PaddleOCR for recognition, a redaction algorithm applies anonymisation using Python's computer vision tools. The system ensures efficient, reliable license plate redaction with minimal computational resource demands. Applicable in law enforcement, traffic analysis, parking, and toll systems, this tool enhances privacy and public safety while improving operational efficiency.
    Keywords: license plate redaction; NVIDIA Deepstream; Yolo model; PaddleOCR; artificial intelligence; video analytics; computer vision; object detection; deep learning.
    DOI: 10.1504/IJAISC.2024.10068008
     
  • SummaSense: An AI-Powered Web Application for Multilingual Text, Audio, and Video Summarisation   Order a copy of this article
    by Gaurav Singh, Advait Nurani, Hridayesh Padalkar, Dr.Reshma Gulwani 
    Abstract: In the era of information overload, the ability to effectively summarise vast amounts of information has become a necessity. This paper introduces SummaSense, an AI-powered web application that utilises both extractive and abstractive summarisation techniques, including KL, LSA, BART, and Conversation BART, to summarise text, audio, and video content in multiple languages. The systems architecture employs Next.js, TailwindCSS, Flask, Node.js, and MongoDB technology, ensuring scalability, robustness, and high-performance results. The systems utility is demonstrated by presenting numerous use cases and scenarios that benefit various businesses and their users. The paper provides a detailed description of the systems features, architecture, implementation, models used, comparisons, testing, and applications, along with several examples of summaries and titles generated by the web application and a comparison with human-generated summaries. The systems effectiveness is demonstrated by presenting several examples of summaries and titles generated by the web application, along with a comparison to human-generated summaries.
    Keywords: Summarization; Multimedia Summarization; Multilingual Summarization; Artificial Intelligence; Natural Language Processing; Deep Learning; KL-Sum Model; LSA Model; BART Model; T5 Model; BART Model.
    DOI: 10.1504/IJAISC.2024.10068991
     
  • Comparative Analysis of Machine Learning Models for Predicting Online Loan Defaults in Nigeria   Order a copy of this article
    by Samuel Faluyi, Peter Idowu, Gbenga O. Ogunsanwo, Olumuyiwa B. ALABA 
    Abstract: The purpose of this study is to carry out a comparative analysis of machine learning models developed for online loan defaulters' prediction. This paper adopted four machine learning approaches, which include random forest, XGBoost, CatBoost and AdaBoost algorithms for predictions of online loan defaulters. The dataset used consists of loan transactions carried out within 2017 in Nigeria's online loan company (super lender), obtained from the Zindi dataset repository. The data comprises 4346 instances and 21 attributes. The data was cleaned and pre-processed before the models were fitted using Python 3.8 Jupyter Notebook environment for simulation and were validated using standard performance metrics, which include the accuracy measure, f1-score, precision, recall, and AUC-ROC score. Based on the results of the study it was identified that CatBoost outperformed other algorithms based on comparison of the performance. Thus, the paper concluded that CatBoost and AdaBoost can be incorporated into online loan systems to determine borrowers' creditworthiness.
    Keywords: Online Loan Default; Machine Learning; Performance Metric; Creditworthiness.
    DOI: 10.1504/IJAISC.2024.10069141
     
  • Enhanced Transfer Learning Techniques: a Resilient Multi-Model Framework for Multi-Class MRI Brain Tumour Diagnosis   Order a copy of this article
    by Rashmi Jolhe, Sudhir Sawarkar 
    Abstract: The diagnosis of brain tumours is difficult and primarily dependent on manual MRI evaluations, which can be laborious and prone to mistakes. We suggest a transfer learning strategy that makes use of pre-trained deep neural networks for effective MRI-based tumour classification in order to enhance this procedure. Our strategy handles the complexity of tumour detection and achieves 97.71% accuracy by fine-tuning six models. For radiologists, this model is a useful tool that improves diagnostic confidence and accuracy. Practical application in clinical settings is ensured by validation using real-world hospital data and a Kaggle dataset.
    Keywords: Deep learning; Glioma; Meningioma; Pituitary ; Perfusion MRI.
    DOI: 10.1504/IJAISC.2024.10069150