Artificial Intelligence (AI) is only as good as its training data. Large training sets with variants on the same classifier improve AI performance and accuracy, especially in image processing systems. Obtaining these large amounts of training data required for training AI and deep neural networks, is laborintensive, expensive and in some cases not possible. This article explores creating a synthetic image dataset of basic electronic components by using the Blender 3D software package to automatically generate large amounts of synthetic images and image augmentation to expand the synthetic dataset. A YOLOv5 classifier model was trained on the resulting synthetic data, and the performance of the model was evaluated using a set of real-world and synthetic testing images. The results show that good-quality synthetic data that accurately represent real-world electronic components can be used to successfully train a deep learning classifier, leading to cost and time savings in the data acquisition process. However, it also shows that synthetic data that does not accurately represent real-world electronic components is of no use and will reduce the overall performance of the classifier.

Smart Cities is a research domain that focuses on achieving sustainable development amidst population growth. One key facet within the realm of smart city research is the exploration of smart sustainable farming. A facet of smart farming aims to address the challenges of land scarcity or arid and semiarid zones and smart urban farming. A research domain of smart farming research is enhancing animal feeding and nutrition in arid and semi-arid zones that could also be aimed towards urban farming. Smart farming technology that addresses challenges is hydroponic green fodder systems. Hydroponic green fodder is an efficient and economical alternative to obtain food for livestock using a small footprint and is not climate dependent. Hydroponic green fodder systems are typically greenhouse feedlot systems that grow plants without soil but in nutrient-rich solutions. These systems have continued production throughout the year. This paper demonstrates the implementation and assessment of a digital airflow twin, derived from a real-world hydroponic green fodder system. The system in question consists of a 24-meter square and produces 750kg of barley sprouts a day that could feed either 375 sheep/goats or 75 cattle in a pen or enclosure. The efficiency of airflow within the hydroponic green fodder system significantly impacts crop yield. To enhance this efficiency, a digital twin could be a valuable tool, enabling timely and costeffective optimization strategies. Two configurations are evaluated one standard, and one improved design as implemented. The digital twin can be used to monitor the Cyber-physical system and has already shown an improvement to the system. The results are analyzed to what was observed from the real-world setup, and recommendations and discussions also highlight the benefits of using digital twins.

Integration of artificial intelligence in industrial automation has led to significant advancements in new techniques for automation. Such an aspect of industrial automation includes sorting consumables on conveyor belt systems via image processing. Typically, these applications use expensive dedicated, and focus-driven hardware and individual image-processing coding. This paper discusses the development of such an imageprocessing sorting conveyor belt but utilizing low-cost processors compared to dedicated and focus-driven hardware. This is achieved by using at the core of this system a Convolutional Neural Network (CNN), specifically tailored for hue-based image processing, and implemented on a Raspberry Pi 4B. A standard Pi camera, attached to the Raspberry Pi, captures images for realtime object classification. A key innovation of the system is the utilization of a pixel-based trigger mechanism for image capture, which significantly improves the accuracy and efficiency of the sorting process. The system achieves an accuracy rate of 92.74% in classifying objects as trained, underscoring the efficacy of the approach. Additionally, the system operates in a dual-mode capacity, enabling not only the sorting of existing object types but also the learning and adaptation to new objects through user input. This feature enhances the system's versatility and applicability in various industrial contexts. The paper details the design, implementation, and testing of this AI-driven sorting mechanism, highlighting its potential as a scalable and low-cost solution for modern industrial sorting needs.