{
    "@context": "https://schema.org",
    "@type": "ScholarlyArticle",
    "identifier": {
        "jsc_id": 35,
        "DOI": "10.5281/zenodo.22995355",
        "DOI_url": "https://doi.org/10.5281/zenodo.22995355"
    },
    "title": "An IoT-Enabled Smart Supply Chain Management Framework: Integrating Real-Time Visibility, Traceability, and LSTM-Based Demand Forecasting",
    "abstract": "The increasing complexity of global supply chains, amplified by major disruptions such as the COVID-19 pandemic, has made advanced digital technologies central to supply chain resilience and operational efficiency. This paper proposes IoT-SCM-Vision, a four-layer Internet of Things (IoT) architecture designed to improve real-time supply chain visibility, end-to-end product traceability, and demand-forecasting accuracy. The framework integrates heterogeneous IoT sensors at the perception layer; an MQTT-based communication layer with edge computing nodes; an intelligence layer that combines Long Short-Term Memory (LSTM) demand forecasting with autoencoder-based anomaly detection; and a decision-support layer that converts model outputs into managerial recommendations. On a simulated five-tier supply chain with twelve months of multi-product data, IoT-SCM-Vision attains a Mean Absolute Percentage Error (MAPE) of 4.73% for demand forecasting, outperforming ARIMA (9.12%) and a simple recurrent neural network (6.84%). Relative to a non-IoT baseline, it also reduces inventory holding costs by 18.2%, increases on-time delivery by 22.7%, and shortens disruption detection time from 48.2 hours to 3.7 hours. The results indicate that integrating IoT sensing with learning-based analytics can improve operational performance across multiple supply-chain metrics.",
    "authors": [
        {
            "sequence": "first",
            "given": "Milad",
            "family": "javadi",
            "name": "Milad javadi",
            "affiliation": [
                {
                    "name": "Economics, School of Economic, Political and Policy Sciences (EPPS), The University of Texas at Dallas, Richardson, Texas, USA"
                }
            ],
            "email": "Milad.javadi@utdallas.edu",
            "is_corresponding": true
        }
    ],
    "keywords": [
        "Internet of Things",
        "Supply Chain Management",
        "Demand Forecasting",
        "Long Short-Term Memory",
        "Real-Time Visibility"
    ],
    "section": "Research Article",
    "language": "en",
    "journal": {
        "name": "Journal of Smart Computing",
        "abbreviation": "JSC",
        "issn": "2979-8752",
        "publisher": "Center of Intelligent Operations and Technology Research, United Kingdom",
        "url": "https://ciotr.com/jsc/"
    },
    "issue": {
        "volume": 1,
        "number": 1,
        "year": 2025,
        "url": "https://ciotr.com/jsc/issue/3"
    },
    "pages": {
        "first": "63",
        "last": "75",
        "range": "63-75"
    },
    "dates": {
        "submitted": "2026-07-25",
        "published": "2025-12-17"
    },
    "urls": {
        "landing_page": "https://ciotr.com/jsc/article/35",
        "pdf": "https://ciotr.com/jsc/pdf/article-35.pdf",
        "metadata": "https://ciotr.com/jsc/article/35.json"
    },
    "license": {
        "name": "Creative Commons Attribution 4.0 International",
        "code": "CC BY 4.0",
        "url": "https://creativecommons.org/licenses/by/4.0/"
    },
    "citation": {
        "apa": "javadi, M. (2025). An IoT-Enabled Smart Supply Chain Management Framework: Integrating Real-Time Visibility, Traceability, and LSTM-Based Demand Forecasting. Journal of Smart Computing, 1(1), 63-75. https://doi.org/10.5281/zenodo.22995355"
    }
}