The production of date paste from second-grade date fruits is a fast-growing industrial activity which promotes more sustainable food systems. The industrial date paste process is mainly dependent on the thermal treatments of hydration and drying that precede flesh crushing. These thermal treatments are commonly performed industrially using steam hydration instead of water soaking and convective hot air drying, which are known to be energy-intensive operations leading to high greenhouse gas emissions. The objective of this work was to optimize, on the one hand, the operations of hydration and drying of dates at an industrial scale using a response surface Box–Behnken experimental design in order to reduce the energy consumption and, on the other hand, to assess the biochemical and microstructural properties of date paste produced under optimized conditions. Optimization was performed based on the measurements of sensory attributes, instrumental texture firmness, moisture content, water activity (a_w), and color parameters (L*, a*, b*), as well as on the energy savings related to the factors of hydration duration and temperature and time of drying. The optimal conditions to ensure the highest quality of the final product and the lowest energy consumption were 9.6 min of hydration at 80 °C and 3 h of drying at 52.28 °C. The biochemical analysis of the date paste produced under the optimized process showed that it is rich in dietary fibers (9.80 ± 2.10%) and total phenols (261 ± 6.2 mg gallic acid equivalent/100 g of extract). Furthermore, the studied sample exhibited a higher antioxidant potential than the raw date material as a result of the heat-inhibitory effect of oxidases. The obtained results suggest that date paste presents a good source of natural bioactive molecules and could potentially be considered as a functional food ingredient. SEM analysis showed that the microstructural properties of date paste produced under optimal conditions may promote its quality preservation during storage.

This study presents an AI-powered approach to enhance quality control and traceability in the agri-food sector, focusing on the automated detection and classification of two Tunisian date varieties: Deglet Nour and "Bsir". The main objective is to develop a smart system that can quantitatively and qualitatively determine the proportion of any contamination of one variety by the other within a batch. To achieve this, state-of-the-art object detection YOLO models, v8 and v12, have been employed, trained on a custom annotated dataset which includes a wide range of real-world images, capturing the variability in the studied date fruit size, shape, and presentation. Both YOLO models were fine-tuned over 50 epochs using transfer learning techniques, allowing them to adapt effectively to the specific classification task. Training step consisted of a thorough analysis of bounding box distributions and samples clustering, taking into account natural variations in date morphology based on their 2D images. Evaluation showed that both models achieved high detection accuracy, with YOLOv12 outperforming slightly in precision and speed, making it well-suited for real-time applications. By estimating the relative variety proportions within a mixed batch, the developed smart system supports the intelligent decision-making across the supply chain. This work lays the groundwork for embedding deep learning models into portable smart optical devices that can assess date mixtures on-site, from farms to packaging centers. Future developments will focus on expanding detection to additional date varieties and integrating the system into commercial post-harvest processes.