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 Articles will not be published until the final proofs are validated by their authors.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

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

International Journal of Artificial Intelligence and Soft Computing (5 papers in press)

Regular Issues

  • An extensive three-tiered architecture for comprehensive crop and fertilizer prediction using supervised learning   Order a copy of this article
    by Abhinav Singh Roy, Sarvika Tiwari, Shubham Wawale, Soham Talekar, Pallavi V. Chavan 
    Abstract: Agriculture accounts for 19.9% of Indias gross domestic product. However, the research and development in this sector do not reflect the massive share of its contribution to our economy. A lot of agricultural activities are still conducted in an archaic manner with little to no thought given to a data-led approach to maximizing yield and profits. Crop yield prediction is a demanding but stimulating hurdle in the agricultural domain as it is contingent on various soil, environmental and geographical factors. It is a crucial step for systematic agronomy to maximize profits while maintaining soil health. Suitable fertilizer selection is paramount not only in optimizing crop yield but also in conserving soil fertility and quality. In this paper, the authors present an extensive threetiered architecture for comprehensive crop and fertilizer prediction. The authors use large amounts of historical data (which is freely available in the public domain) to train the model with different variables such as soil pH, moisture and temperature in mind. A three-tiered solution is proposed which focuses on predicting a crop based on the area under cultivation and geographical region. The yield for the given crop is predicted. The second tier focuses on predicting the cost of cultivation for the given crop and the area under cultivation. Finally, a fertilizer is predicted for the given crop based on soil nutrient and environmental factors in the third tier. Crop Prediction implemented through The Random Forest Classifier gave 99.54% accuracy. Yield Prediction determined using Linear Regression yielded 89.57% accuracy. Naive Bayes algorithm used to predict the fertilizer for a given crop provided 100% accuracy.
    Keywords: Naive Bayesian; Random Forest Classification; Linear Regression; Supervised Learning; Prediction.

  • Fuzzy logic-based optimization of Aloha protocol in wireless networks under different traffic loads   Order a copy of this article
    by Ridhima Mehta 
    Abstract: Random and decentralized channel access by hosts in the wireless broadcast network is highly susceptible to packet collisions, information loss and alleviated system throughput. The slotted Aloha method is a random multiple-access resolution protocol at the data link layer for data transmission across the shared communication path in synchronized way. In this paper, we propose a novel adaptive, throughput-efficient and fully-distributed slotted Aloha protocol based on the fuzzy logic design. Distinct network attributes are modeled using the multivariate fuzzy logic controller. The fuzzy inputs employed in the presented system include the propagation delay of wireless radio links, network size, and packet length. Moreover, the slot duration and the transmission rate constitute the two fuzzy outputs. Through extensive simulation experiments and analysis, the developed optimization model is compared with the standard Aloha protocol under diverse traffic load distributions. The simulation results demonstrate the enhanced performance of the Aloha wireless network implemented with fuzzy decision-making over the conventional Aloha systems. The deployed performance parameters for comparative assessment incorporate the collision multiplicity, channel utilization, collision rate, and throughput.
    Keywords: Fuzzy logic; Membership function; Slotted Aloha protocol; Throughput.

  • A Distributed Group Mutual Exclusion Algorithm for IoT systems   Order a copy of this article
    by Bouneb Zine El Abidine 
    Abstract: The group mutual exclusion problem is a specific instance of the ME problem. In this instance, processes that request the same resources, known as a group, are allowed to be in their critical section (CS) simultaneously. However, processes that request different resources must execute their CS in a mutually exclusive way. In this paper, we consider groups in the context of bound and unbound resources. This classification introduces a new type of distributed mutual exclusion algorithm that is based on the publish/subscribe paradigm. In this paradigm, a process can belong to multiple groups based on the requested resources.
    Keywords: publish-subscribe; Group mutual exclusion; distributed algorithm,Maximal cliques; distributed Bron-Kerbosch algorithm; IoT.

  • Prediction of Dengue Fever using Supervised Machine Learning based on Hyperparameter tuning and an analysis of the factors influencing dengue spread   Order a copy of this article
    by Harshita Mandalika, Manya Rampuria, Nenavath Srinivas Naik 
    Abstract: Dengue is a mosquito?borne arboviral disease infecting humans. Studies analyzed the spread of dengue by considering climatic factors alone. However, its transmission does not depend only on climatic factors. This paper focuses on finding the contribution of climatic features in predicting dengue fever and the other factors affecting its transmission. To achieve this, various data preprocessing steps and feature selection are done to drop the non-essential data. Hyper-parameter optimization is done to tune the different machine learning models, which are then deployed. The best-fit model for San Juan and Iquitos data is based on the evaluation metrics. For San Juan City, the best performance is obtained by the XG Boost model and the Random Forest model for Iquitos City. However, the results explain that only climatic features are insufficient in predicting the dengue cases. Immunity, infecting serotype, hygiene, precautions taken, and the secondary vectors also affect its spread.
    Keywords: Dengue Prediction; Supervised Machine Learning; Correlation; Hyperparameter Optimization; Climatic Features; Factors Affecting Dengue spread.

  • Integrated AWA Fitness PSO-SPICE Framework for Automated Design and Optimization of Analog and Mixed-Signal ICs   Order a copy of this article
    by Harsha M. V., B.P. Harish 
    Abstract: The design and optimization of analog and mixed-signal integrated circuits become intractable with technology scaling. It gives rise to multi-dimensional tradeoffs among its numerous performance metrics. Evolutionary algorithms are being explored to generate possible solutions having goodness of fit with the desired solution. In this direction, a novel fitness evaluation function integrated with PSO and PSO- SPICE framework is proposed to design and implement multi-objective optimization for analog and mixed-signal circuit design automation. The framework is demonstrated to automatically design and optimize the multi-objectives of 2-stage op-amp and 4-bit ash ADC. The proposed fitness evaluation function demonstrate large design outperformance independent of quality of initial population and requiring no adaptive weights. The novel fitness function driven PSO-SPICE framework exemplifies a robust, scalable, and precise method for multi-objective optimization of analog and mixed-signal circuits of varying scale and design complexity.
    Keywords: PSO; 2-stage op-amp; Flash ADC; Multi-objective optimization; AWA fitness function.