This study examines the application of agentic artificial intelligence (AI) frameworks within small, medium, and micro-enterprises (SMMEs), highlighting how interconnected autonomous agents improve operational efficiency and adaptability. Using the PRISMA 2020 framework, this study systematically identified, screened, and analyzed 66 studies, including peer-reviewed and credible gray literature, published between 2019 and 2024, to assess agentic AI frameworks in SMMEs. Recognizing the constraints faced by SMMEs, such as limited scalability, high operational demands, and restricted access to advanced technologies, the review synthesizes existing research to highlight the characteristics, implementations, and impacts of agentic AI in task automation, decision-making, and ecosystem-wide collaboration. The results demonstrate the potential of agentic AI to address technological, ethical, and infrastructure barriers while promoting innovation, scalability, and competitiveness. This review contributes to the understanding of agentic AI frameworks by offering practical insights and setting the groundwork for further research into their applications in SMMEs’ dynamic and resource-constrained economic environments.

The devastating effects of rain-induced attenuation on communication links operating above 10 GHz during rainy events can significantly degrade signal quality, leading to interruptions in service and reduced data throughput. Understanding the spatial and seasonal distribution of rain heights is crucial for predicting these attenuation effects and for network performance optimization. This study utilized ten years of atmospheric temperature and geopotential height data at seven pressure levels (1000, 850, 700, 500, 300, 200, and 100 hPa) obtained from the Copernicus Climate Data Store (CDS) to deduce rain heights across nine stations in South Africa. The kernel density estimation (KDE) method was applied to estimate the temporal variation of rain height. A comparison of the measured and estimated rain heights shows a correlation coefficient of 0.997 with a maximum percentage difference of 5.3%. The results show that rain height ranges from a minimum of 3.5 km during winter in Cape Town to a maximum of about 5.27 km during the summer in Polokwane. The spatial variation shows a location-dependent seasonal trend, with peak rain heights prevailing at the low-latitude stations. The seasonal variability indicates that higher rain heights dominate in the regions (Polokwane, Pretoria, Nelspruit, Mahikeng) where there is frequent occurrence of rainfall during the winter season and vice versa. Contour maps of rain heights over the four seasons (autumn, spring, winter, and summer) were also developed for South Africa. The estimated seasonal rain heights show that rain-induced attenuations were grossly underestimated by the International Telecommunication Union (ITU) recommended rain heights at most of the stations during autumn, spring, and summer but fairly overestimated during winter. Durban had a peak attenuation of 15.9 dB during the summer, while Upington recorded the smallest attenuation of about 7.7 dB during winter at a 0.01% time exceedance. Future system planning and adjustments of existing infrastructure in the study stations could be improved by integrating these localized, seasonal radio propagation data in link budget design.

Solar energy has become the fastest growing renewable and alternative source of energy. However, there is little or no open-source datasets to advance research knowledge in photovoltaic related systems. The work presented in this article is a step towards deriving Photo-Voltaic Module Dataset (PVMD) of thermal images and ensuring they are publicly available. The work provides a PVMD dataset comprising a total of 1000 self-acquired and augmented images. The dataset includes both permanent and temporal anomalies, namely Hotspots, Cracks, and Shadings. The dataset was collected on September 5, 2024 at the Soshanguve South Campus, Tshwane University of Technology, South Africa using DJI Mavic 3 Thermal's high-resolution thermal and visual imaging capabilities. DJI Mavic 3 Thermal coupled with its advanced flight features makes it an excellent tool for precise and efficient inspections of PV systems. The laboratory experiment performed on the dataset lasted one week. The work aims to provide supervised dataset good enough to support research method in providing a comprehensive and efficient approach to monitoring and maintaining large PV systems. Extensive analysis of the thermal data reveals the anomalies as indicative of faults in the solar cells of PV module, thereby opening up advancement in solar energy research. Because the data comes from a single-day collection and one week laboratory experiment, it makes the data more suitable for testing algorithms designed for fault detection. The dataset is publicly and freely available to the scientific community at 10.17632/5ssmfpgrpc.1

Cloud-based license plate recognition (LPR) systems have emerged as essential tools in modern traffic management and security applications. Determining the best approach remains paramount in the field of computer vision. This study presents a comparative analysis of various versions of the YOLO (You Only Look Once) object detection models, namely, YOLO 5, 7, 8, and 9, applied to LPR tasks in a cloud computing environment. Using live video, we performed experiments on YOLOv5, YOLOv7, YOLOv8, and YOLOv9 models to detect number plates in real time. According to the results, YOLOv8 is reported the most effective model for real-world deployment due to its strong cloud performance. It achieved an accuracy of 78% during cloud testing, while YOLOv5 showed consistent performance with 71%. YOLOv7 performed poorly in cloud testing (52%), indicating potential issues, while YOLOv9 reported 70% accuracy. This tight alignment of results shows consistent, although modest, performance across scenarios. The findings highlight the evolution of the YOLO architecture and its impact on enhancing LPR accuracy and processing efficiency. The results provide valuable insights into selecting the most appropriate YOLO model for cloud-based LPR systems, balancing the trade-offs between real-time performance and detection precision. This research contributes to advancing the field of intelligent transportation systems by offering a detailed comparison that can guide future implementations and optimizations of LPR systems in cloud environments.

Background: Accurate subtype identification of lymphoma cancer is crucial for effective diagnosis and treatment planning. Although standard deep learning algorithms have demonstrated robustness, they are still prone to overfitting and limited generalization, necessitating more reliable and robust methods. Objectives: This study presents an autoencoder-augmented stacked ensemble learning (SEL) framework integrating deep feature extraction (DFE) and ensembles of machine learning classifiers to improve lymphoma subtype identification. Methods: Convolutional autoencoder (CAE) was utilized to obtain high-level feature representations of histopathological images, followed by dimensionality reduction via Principal Component Analysis (PCA). Various models were utilized for classifying extracted features, i.e., Random Forest (RF), Support Vector Machine (SVM), Multi-Layer Perceptron (MLP), AdaBoost, and Extra Trees classifiers. A Gradient Boosting Machine (GBM) meta-classifier was utilized in an SEL approach to further fine-tune final predictions. Results: All the models were tested using accuracy, area under the curve (AUC), and Average Precision (AP) metrics. The stacked ensemble classifier performed better than all the individual models with a 99.04% accuracy, 0.9998 AUC, and 0.9996 AP, far exceeding what regular deep learning (DL) methods would achieve. Of standalone classifiers, MLP (97.71% accuracy, 0.9986 AUC, 0.9973 AP) and Random Forest (96.71% accuracy, 0.9977 AUC, 0.9953 AP) provided the best prediction performance, while AdaBoost was the poorest performer (68.25% accuracy, 0.8194 AUC, 0.6424 AP). PCA and t-SNE plots confirmed that DFE effectively enhances class discrimination. Conclusion: This study demonstrates a highly accurate and reliable approach to lymphoma classification by using autoencoder-assisted ensemble learning, reducing the misclassification rate and significantly enhancing the accuracy of diagnosis. AI-based models are designed to assist pathologists by providing interpretable outputs such as class probabilities and visualizations (e.g., Grad-CAM), enabling them to understand and validate predictions in the diagnostic workflow. Future studies should enhance computational efficacy and conduct multi-centre validation studies to confirm the model’s generalizability on extensive collections of histopathological datasets.