Accurate, forward-looking sales forecasts are a prerequisite for effective retail supply chain optimization, informing procurement, warehousing, and replenishment decisions well before demand materialises. This study develops a lag-feature-based machine learning forecasting framework for monthly, category-level retail revenue, using a transactional e-commerce dataset of 5,000 orders spanning four product categories over a multi-year horizon. Historical revenue, quantity, discount, and order-count values were aggregated into a category-month panel (647 usable observations after lag construction) and enriched with first-, second-, and third-order revenue lags and a three-month rolling mean, following established lag-feature forecasting practice. Six forecasting approaches were compared on a chronologically held-out test period: a naive persistence baseline, a three-month moving-average baseline, Linear Regression, Random Forest, Gradient Boosted Trees, and a windowed Artificial Neural Network (Multilayer Perceptron). Because the specialised recurrent deep-learning architectures originally specified for this study: Long Short-Term Memory (LSTM), Gated Recurrent Unit (GRU), and Bidirectional GRU (Bi-GRU) networks require TensorFlow or PyTorch, and these libraries (together with internet access to install them) were unavailable in the computational environment used for this research, the windowed MLP is reported explicitly as a substitute deep-learning benchmark rather than as a recurrent architecture, and this substitution is discussed in detail as a limitation. Linear Regression achieved the strongest held-out performance (RMSE = $1,762, R² = 0.831, MAPE = 23.96%), narrowly ahead of Random Forest (R² = 0.811) and Gradient Boosted Trees (R² = 0.794), while both baselines and the windowed MLP underperformed the regression-based learners. Feature-importance analysis showed that order quantity, rather than the revenue lags themselves, was overwhelmingly the dominant predictor (90.7% relative importance) a finding attributable to the near-deterministic relationship between quantity, unit price, and revenue in this dataset. The study concludes that classical regression and ensemble methods, when combined with carefully engineered lag and rolling-window features, provide an accurate and computationally inexpensive foundation for supply chain demand forecasting, and outlines a concrete roadmap including LSTM/GRU/Bi-GRU implementation once suitable deep-learning infrastructure is available for extending this framework toward sequence-aware, uncertainty-calibrated forecasting.

]]> Sales Forecasting, Supply Chain Optimization, Lag Features, Machine Learning, Time-Series Regression, Retail Demand Research Article Thu, 27 Aug 2026 00:00:00 IST The adoption of emerging technologies for knowledge management (KM) in academic libraries presents significant opportunities for enhancing information organisation, dissemination, and institutional memory preservation, particularly in resource-constrained regions such as North-East Nigeria. This study investigated the adoption of emerging technologies for knowledge management in academic libraries in the North-East geopolitical zone of Nigeria. A descriptive survey design was employed, targeting 389 library professionals across 18 academic libraries (universities, polytechnics, and colleges of education) in the six states of the zone. Data were collected using a structured questionnaire (Cronbach's α = 0.88) and analysed using SPSS version 29 for descriptive statistics and one-way ANOVA, and SmartPLS version 4 for PLS-SEM path modelling. Python 3.11 generated supplementary visualisations. Findings indicated moderate overall technology adoption (Grand Mean = 3.72), with cloud computing (Mean = 4.38) and digital repository systems (Mean = 4.21) as the most adopted technologies. Knowledge management benefits were highly perceived (Grand Mean = 4.32), while barriers were equally prevalent (Grand Mean = 4.37), with poor ICT infrastructure (Mean = 4.63) and inadequate funding (Mean = 4.58) as the foremost impediments. SmartPLS SEM confirmed that technology readiness significantly predicted ET adoption (β = 0.623, t = 13.84, p < 0.001), which in turn predicted KM effectiveness (β = 0.587, p < 0.001). One-way ANOVA revealed significant adoption differences by designation (F (3,385) = 21.38, p < .001). The study recommends technology readiness programmes, institutional KM policy formulation, and consortium-based infrastructure investment.

]]> Emerging Technologies, Knowledge Management, Academic Libraries, North-East Nigeria, SmartPLS, Cloud Computing Research Article Thu, 27 Aug 2026 00:00:00 IST Deep learning has become a dominant paradigm for financial time series forecasting, yet comparative evidence on which recurrent architecture performs best for emerging-market return forecasting remains limited. This study conducts a systematic comparative analysis of three recurrent deep learning architectures: Long Short-Term Memory (LSTM), Gated Recurrent Unit (GRU) and Simple Recurrent Neural Network (Simple RNN) for forecasting one-day-ahead logarithmic returns of the Nigerian Stock Exchange (NSE) All-Share Index using 2,221 daily observations spanning January 2015 to December 2023, supplemented with a contextual update on the index's trajectory through July 2026 drawn from publicly reported market data. Eleven technical predictors were transformed into fifteen-day rolling sequences and used to train each architecture, implemented from first principles in Python/NumPy with an identical sixteen-hidden-unit configuration, Adam optimisation and chronological train-validation-test partitioning to ensure a controlled, like-for-like comparison. Model performance was evaluated on the held-out test set using root mean squared error (RMSE), mean absolute error (MAE), mean absolute percentage error (MAPE) and the coefficient of determination (R²), benchmarked against a random-walk naive forecast and a random forest regressor. The LSTM achieved the lowest error among the three recurrent architectures (RMSE = 0.00846, MAE = 0.00571), outperforming GRU (RMSE = 0.00968) and Simple RNN (RMSE = 0.00934) and comfortably beating the naive random-walk benchmark (RMSE = 0.01045), while a random forest baseline achieved the lowest overall error (RMSE = 0.00827) among all five models evaluated, and the least negative R² (-0.016), though all models produced R² values below zero, reflecting the difficulty of explaining out-of-sample daily return variance for a single equity index. These results confirm the general superiority of gated recurrent architectures, and LSTM in particular, over simple recurrent networks for return forecasting, while also demonstrating that the marginal advantage of deep sequence models over well-tuned ensemble methods remains small for a single-index return series, consistent with weak-form market efficiency. The paper provides a transparent, reproducible comparative benchmark for deep learning-based return forecasting on the NSE and offers practical guidance for architecture selection in frontier-market applications.

]]> Deep Learning, LSTM, GRU, Recurrent Neural Network, Nigerian Stock Exchange, Stock Return Forecasting, Comparative Analysis Research Article Thu, 27 Aug 2026 00:00:00 IST Industrial Internet of Things (IIoT) technologies have transformed modern industrial environments by enabling intelligent automation, real-time monitoring, predictive maintenance, and smart manufacturing operations. However, the rapid adoption of interconnected industrial devices has introduced significant cybersecurity challenges including unauthorized access, ransomware attacks, data breaches, distributed denial-of-service attacks, and network intrusions. Traditional security mechanisms are insufficient to protect large-scale IIoT infrastructures due to device heterogeneity, limited computational capabilities, and dynamic industrial environments. This paper proposes an Artificial Intelligence-based Industrial IoT security framework integrating machine learning and blockchain technologies for secure industrial communication and intelligent threat detection. The proposed framework employs IoT sensors, edge computing, cloud infrastructure, and AI-driven intrusion detection models to identify malicious activities in industrial networks. Blockchain technology is incorporated to ensure secure data sharing, authentication, and tamper-resistant communication among IIoT devices. Experimental analysis demonstrates improved detection accuracy, reduced false-positive rates, enhanced network security, and efficient real-time monitoring compared with conventional IIoT security approaches. The proposed system offers a scalable and intelligent solution suitable for Industry 4.0 and smart manufacturing environments.

]]> Industrial Internet of Things, Artificial Intelligence, Machine Learning, Blockchain, Cybersecurity, Intrusion Detection, Smart Manufacturing, Industry 4.0 Review Article Wed, 20 May 2026 00:00:00 IST Rapid urban growth and the rising number of vehicles on roads have created serious challenges such as heavy traffic congestion, increased road accidents, excessive fuel usage, and higher levels of environmental pollution in urban areas. Conventional traffic management methods mainly depend on fixed-time traffic signals and manual supervision, which are often unable to respond effectively to changing traffic patterns and real-time road conditions. To address these limitations, the adoption of Artificial Intelligence (AI) and Internet of Things (IoT) technologies has enabled the development of smart traffic management systems that support real-time traffic monitoring, predictive analysis, and automated traffic regulation. This paper presents an AI-IoT-based intelligent traffic management framework integrating smart sensors, machine learning algorithms, edge computing, and cloud infrastructure for efficient traffic monitoring and congestion control. The proposed system continuously collects traffic data through IoT-enabled cameras, vehicle sensors, RFID devices, and smart traffic signals. Machine learning algorithms analyze traffic patterns, predict congestion levels, and optimize traffic signal operations dynamically. The framework supports emergency vehicle prioritization, accident detection, and intelligent route management for smart city transportation systems. Experimental analysis demonstrates improved traffic flow efficiency, reduced congestion rates, minimized waiting time, and enhanced traffic prediction accuracy compared with conventional traffic management approaches. The proposed framework provides a scalable and intelligent solution suitable for smart city transportation infrastructures and sustainable urban mobility.

]]> Intelligent Traffic Management, Artificial Intelligence, Internet of Things, Smart Cities, Machine Learning, Traffic Prediction, Smart Transportation, Congestion Control Review Article Wed, 20 May 2026 00:00:00 IST Environmental pollution and climate change have become major global concerns affecting human health, biodiversity, agriculture, and industrial sustainability. Traditional environmental monitoring systems often rely on manual observation methods and isolated sensing mechanisms, which are inefficient for real-time analysis and predictive decision-making. The integration of Artificial Intelligence (AI) and Internet of Things (IoT) technologies has introduced intelligent environmental monitoring solutions capable of continuous sensing, automated analysis, and early hazard prediction. This paper presents an AI-based environmental monitoring framework integrating IoT sensors, cloud computing, and machine learning algorithms for real-time monitoring of environmental conditions. The proposed system collects data related to air quality, temperature, humidity, water quality, noise levels, and gas emissions using IoT-enabled smart sensors. Machine learning techniques are employed to analyze environmental patterns and predict pollution levels and hazardous conditions. Cloud infrastructure facilitates centralized data storage, remote monitoring, and intelligent analytics. Experimental analysis demonstrates improved monitoring accuracy, efficient anomaly detection, and faster environmental response compared with conventional monitoring systems. The proposed framework offers a scalable, cost-effective, and intelligent solution for smart cities and sustainable environmental management.

]]> Environmental Monitoring, Artificial Intelligence, Internet of Things, Machine Learning, Smart Sensors, Pollution Detection, Smart Cities, Predictive Analytics Review Article Wed, 20 May 2026 00:00:00 IST The rapid growth of Internet of Things (IoT) technologies and Artificial Intelligence (AI) has significantly transformed modern healthcare systems by enabling intelligent monitoring, real-time data analysis, and predictive disease diagnosis. Conventional healthcare systems often experience delays in patient monitoring and disease identification due to limited accessibility and manual analysis procedures. This research presents an AI-based smart healthcare monitoring and predictive disease detection framework integrating IoT sensors with machine learning techniques for continuous health assessment. The proposed system collects physiological parameters such as heart rate, body temperature, blood pressure, oxygen saturation, and glucose levels through IoT-enabled wearable devices. The gathered data are processed using machine learning algorithms to identify abnormalities and predict potential diseases at an early stage. The framework employs cloud-based storage and analytical models to improve healthcare accessibility, accuracy, and remote patient management. Experimental evaluation demonstrates improved prediction accuracy, reduced response time, and efficient monitoring compared with conventional healthcare systems. The proposed model provides a scalable, cost-effective, and intelligent healthcare solution suitable for smart hospitals and remote healthcare environments.

]]> Artificial Intelligence, Internet of Things, Smart Healthcare, Machine Learning, Predictive Analytics, Remote Patient Monitoring, Disease Detection Review Article Wed, 20 May 2026 00:00:00 IST The rapid rise in chronic health conditions, along with the increasing need for remote and accessible healthcare services, has significantly encouraged the integration of Artificial Intelligence (AI) and Internet of Things (IoT) technologies into today’s healthcare systems. Conventional disease diagnosis approaches often depend on periodic medical examinations and manual analysis, which may delay early disease identification and emergency response. This paper presents an AI-IoT framework for intelligent disease prediction and smart healthcare monitoring using machine learning algorithms and IoT-enabled wearable devices. The proposed system continuously collects physiological parameters including heart rate, blood pressure, glucose levels, body temperature, oxygen saturation, and respiratory rate through IoT sensors. The acquired healthcare data are transmitted to cloud platforms for storage and intelligent analysis. Machine learning models are employed to identify abnormal health conditions and predict diseases at early stages. The framework integrates real-time monitoring, cloud computing, predictive analytics, and automated alert generation to improve healthcare accessibility and diagnostic accuracy. Experimental analysis demonstrates improved prediction performance, reduced response time, and enhanced healthcare efficiency compared with conventional healthcare systems. The proposed AI-IoT framework provides a scalable and cost-effective solution suitable for smart hospitals, telemedicine, and remote patient monitoring applications.

]]> Artificial Intelligence, Internet of Things, Disease Prediction, Machine Learning, Smart Healthcare, Predictive Analytics, Remote Monitoring, Healthcare IoT Review Article Wed, 20 May 2026 00:00:00 IST