The complex integration of Industry 4.0 technologies into SMEs necessitates robust frameworks to address adoption barriers and enhance sustainability. The present study investigates the impact of artificial intelligence (AI), the Internet of Things (IoT), and blockchain on smart manufacturing, logistics, and sustainability in SMEs. Using a cross-sectional design, data were collected from 300 SMEs across manufacturing, logistics, and retail sectors through purposive sampling, focusing on technology adoption, and sustainability performance from 2018 to 2022. Data were analyzed using advanced machine learning models, including XG Boost and Random Forest, alongside Recursive Feature Elimination (RFE) for dimensionality reduction and quantile regression for an inferential analysis. Findings revealed that IoT adoption improved resource utilization efficiency, while blockchain enhanced ethical sourcing—furthermore, AI-driven predictive maintenance reduced operational downtimes. XG Boost achieved a Mean Squared Error (MSE), highlighting its superior predictive capability, while Random Forest achieved perfect fitness but risked overfitting. However, adoption varied significantly across firms due to financial and technical constraints, with SMEs reporting limited access to capital and skilled labor. This study underscores the need for policy interventions and targeted support for SMEs to bridge adoption gaps. The study advances the existing body of knowledge by highlighting the synergistic benefits of integrating Industry 4.0 technologies to enhance SME sustainability. Practical implications include policy recommendations for financial incentives, technical support, and capacity-building programs, empowering SMEs with actionable insights to overcome adoption barriers and achieve sustainable growth. These findings offer industry leaders and policymakers’ actionable insights to drive SME transformation in Industry 4.0, empowering them to make a difference.
The sustainable management of energy sources such as wind plays a crucial role in supplying electricity for both residential and industrial purposes. For this, accurate wind data are essential to bring sustainability in energy output estimations for wind stations. The choice of an appropriate distribution function significantly affects the actual wind data, directly influencing the estimated energy output. While the Weibull function is commonly used to describe wind speed at various locations worldwide, the variability of weather information across wind sites varies significantly. Probabilistic forecasting offers comprehensive probability information for renewable generation and load, assisting decision-making in power systems under uncertainty. Traditional probabilistic forecasting techniques based on machine learning (ML) rely on prediction uncertainty derived from previous distributional assumptions. This study utilized a Bayesian Recurrent Neural Network (BNN-RNN), incorporating prior distributions for weight variables in the RNN network layer and extending the Bayesian networks. Initially, a periodic RNN processes data for wind energy prediction, capturing trends and correlation characteristics in time-series data to enable more accurate and reliable energy production forecasts. Subsequently, the wind power meteorological dataset was analyzed using the reciprocal entropy approach to reduce dimensionality and eliminate variables with weak connections, thereby simplifying the structure of the prediction model. The BNN-RNN prediction model integrates inputs from RNN-transformed time-series data, dimensionality-reduced weather information, and time categorization feature data. The Winkler index is lower by 3.4%, 32.6%, and 7.2%, respectively, and the overall index of probability forecasting pinball loss is reduced by 51.2%, 22.3%, and 10.7%, respectively, compared with all three approaches. The implications of this study are significant, as they demonstrate the potential for more accurate wind energy forecasting through Bayesian optimization. These findings contribute to more precise decision-making and bring sustainability to the effective management of energy systems by proposing a Bayesian Recurrent Neural Network (BNN-RNN) to improve wind energy forecasts. The model further enhances future estimates of wind energy generation, considering the stochastic nature of meteorological data. The study is crucial in increasing the understanding and application of machine learning by establishing how Bayesian optimization significantly improves probabilistic forecasting models that would revolutionize sustainable energy management.
Water resource monitoring can provide beneficial information supporting water management; however, present operational systems are small and provide only a subset of the information needed. Primary advancements consist of the clear explanation of water redistribution and water use from groundwater and river schemes, achieving better spatial detail and increased precision as evaluated against hydrometric observation. In such cases, Earth Observation (EO) satellite systems are persistently creating extensive data, which is now essential for applications in different fields. With readily available open-source satellite imagery, aerial remote sensing is progressively becoming a quick and efficient tool for monitoring land and water resource development actions, demonstrating time and cost savings. At present, the deep learning (DL) model will be beneficial for monitoring water resources and EO utilizing remote sensing. In this paper, a Deep Neural Network-Based Object Detection for Water Resource Monitoring and Earth Observation (DNNOD-WRMEO) model is introduced. The main intention is to develop an effective monitoring and analysis framework for water resources and Earth surface observations using aerial remote sensing images. Initially, the Wiener filter (WF) model was used for image pre-processing. For object detection, the Yolov12 method was used for identifying, locating, and classifying objects within an image, followed by the DNNOD-WRMEO methodology, which implements the ResNet-CapsNet model for the backbone feature extraction method. Finally, the temporal convolutional network (TCN) model was implemented for the classification of water resources. The comparison analysis of the DNNOD-WRMEO methodology exhibited a superior accuracy value of 98.61% compared with existing models under the AIWR dataset.
Boolean networks are a widely used qualitative modelling approach which allows the abstract description of a biological system. One issue with the application of Boolean networks is the state space explosion problem which limits the applicability of the approach to large realistic systems. In this paper we investigate developing a compositional framework for Boolean networks to facilitate the construction and analysis of large scale models. The compositional approach we present is based on merging entities between Boolean networks using conjunction and we introduce the notion of compatibility which formalises the preservation of behaviour under composition. We investigate characterising compatibility and develop a notion of trace alignment which is sufficient to ensure compatibility. The compositional framework developed is supported by a prototype tool that automates composition and analysis.
Complex approaches for signal integrity analysis in high-frequency bio-sensing circuits have been developed. This article describes “Machine Learning-Enhanced Signal Integrity Analysis.” It analyses data using random forests, support vector machines, and recurrent neural networks. We compare the proposed technique to Fourier transform, Butterworth filtering, TDR, eye diagram analysis, correlation, and power spectral density to evaluate its efficacy. Precision distribution pie charts, memory distribution violin plots, F1 score distribution box plots, and accuracy comparison scatter plots can highlight the difference. These images demonstrate how successfully the recommended technique removes tiny characteristics from high-frequency bio-sensing data. The accuracy pie chart and memory violin plot demonstrate the approach's success in discovering pleasant experiences. But the false-negative rate demonstrates how effectively it finds false positives. Precision and mental balance are shown by the F1 score box plot, while the accuracy scatter plot compares all data points. Machine learning outperforms earlier approaches in accuracy, precision, memory, and F1 score. Notably, the suggested approach displays proactive error correction methods and flexibility to varying signal circumstances. It also demonstrates computational efficiency by drastically cutting down on training and inference durations in comparison to more conventional approaches. Finally, the provided machine learning-enhanced method not only improves signal integrity analysis in high-frequency bio-sensing circuits, but also establishes a new benchmark in terms of precision, robustness, and versatility. These results highlight the revolutionary potential of applying machine learning to biomedical engineering problems, opening the door to better diagnostics and real-time monitoring in settings with high-frequency signals.