In this paper we present a blockchain based system for the supply chain management of a particular Italian bread. Goal of the system is to guarantee a transparent and auditable traceability of the Carasau bread where each actor of the supply chain can verify the quality of the products and the conformity to the normative about the hygienic-sanitary conditions along the chain. To realize this system we relied on the Blockchain and the Internet of Thing technologies in order to provide a trustless environment, in which trust is placed in cryptography, in mathematical operations and on the network, and not in public or private companies. Thanks to the use of digital technologies the system aims to reduce the data entry errors and the risk of tampering. Our system is designed so that along the supply chain, the nodes equipped with several sensors directly communicate their data to Raspberry Pi units that elaborate and transmit them to Interplanetary File System and to the Ethereum Blockchain. Furthermore, we designed ad hoc Radio Frequency Identification and Near Field communication tags to shortly supply the proposed system with information about the products and batches. The dedicated RFID tags robustness during on-bread operation was numerically tested. The system will easily allow end consumers to have a transparent view on the whole journey from raw material to purchased final product and a supervisory authority to perform online inspections on the products' quality and on the good working practices.

There is a growing demand for transparency along the agri-food chain, both from customers and governments. The adoption of blockchain technology to enable secure traceability for the management of the agri-food chain, provide information such as the provenance of a food product and prevent food fraud, is emerging rapidly, due to the inherent trust and inalterability provided by this technology. However, developing the right smart contracts for these use cases is even more of a challenge than it is for those used in other fields. Several management systems for the agri-food chain based on blockchain technology and smart contract have been proposed, all however ad-hoc for a specific product or production process and difficult to generalize. In this paper, we propose a new approach to easily customize and compose general Ethereum-based smart contracts designed for the agri-food industrial domain, to be able to reuse the code and modules and automate the process to shorten development times, while keeping it safe and reliable. Starting from the definition of the real production process, we aim to automatically generate both the smart contracts to manage the system and the user interfaces to interact with them, thus producing a system that works semi-automatically. Additionally, we describe a honey production case study to show how our approach works. Future work will first extend the scope of the approach to other supply chains, furthermore, while the current platform used is Ethereum, in the future our approach will be easily extended to other blockchain platforms.

In this paper, we address the problem of automatic image segmentation methods applied to the partial automation of the production process of a traditional Sardinian flatbread called pane Carasau for assuring quality control. The study focuses on one of the most critical activities for obtaining an efficient degree of automation: the estimation of the size and shape of the bread sheets during the production phase, to study the shape variations undergone by the sheet depending on some environmental and production variables. The knowledge can thus be used to create a system capable of predicting the quality of the shape of the dough produced and empower the production process. We implemented an image acquisition system and created an efficient machine learning algorithm, based on support vector machines, for the segmentation and estimation of image measurements for Carasau bread. Experiments demonstrated that the method can successfully achieve accurate segmentation of bread sheets images, ensuring that the dimensions extracted are representative of the sheets coming from the production process. The algorithm proved to be fast and accurate in estimating the size of the bread sheets in various scenarios that occurred over a year of acquisitions. The maximum error committed by the algorithm is equal to the 2.2% of the pixel size in the worst scenario and to 1.2% elsewhere.

The knowledge of the electromagnetic field levels generated by radio base stations present in an urban environment is a relevant aspect for propagations and coverage issues, as well as for the compliance to national regulations. Despite the growing interest in the novel fifth generation (5G) technology, several aspects related to the investigation of the urban propagation of the Global System of Mobile Communication (GSM), third generation (3G), and fourth generation (4G) mobile systems in peculiar non-rural environments may be improved. To account for irregular geometries and to deal with the propagation in hilly towns, in this work we present an enhanced version of the COST231-Walfisch–Ikegami model, whose parameters have been modified to evaluate the path loss at distances greater than 20 meters from the radio base station. This work addressed the problem of providing an effective, reliable, and quantitative model for the estimation of electromagnetic field levels in built-up areas. In addition, we also developed and tested a pre-industrial software prototype whose aim is to make the estimated electromagnetic field levels available to the key players in the telecom industry, the local authorities, and the general population. We validated the proposed model with a measurement campaign in the small urban and irregular built-up areas of Dorgali (Nuoro), Cala Gonone (Nuoro), and Lunamatrona (Cagliari) in Sardinia (Italy).

Automated visual quality inspection of artisanal baked goods requires methods that are accurate, interpretable, and capable of distinguishing multiple independent quality dimensions from a single image. We present a dual-target feature engineering framework for ordinal grading of pane Carasau, a traditional Sardinian flatbread with high surface variability, validated on a dataset of 1,512 images spanning four acquisition campaigns and three product types. The pipeline extracts 116 handcrafted visual descriptors organised into four families—colour, texture, spatial, and hotspot—and gradesquality along two independent axes: global toasting intensity and spatialuniformity, complemented by a continuous Toasting Index for process monitoring. On the primary within-campaign set (N = 1,090), XGBoost achievesF1 macro = 0.906 for toast classification and R2 = 0.886 for continuousregression, substantially outperforming two fine-tuned CNN baselines (MobileNetV2: F1 = 0.524; EfficientNet-B0: F1 = 0.518). Feature importance analysis confirms that colour descriptors dominate toasting prediction (87.5%), whilst spatial and texture features are essential for uniformity assessment (46.0% combined). Cross-campaign evaluation on three held-out sets reveals moderate cross-batch generalisation on the same product (XGB F1 = 0.718, κ = 0.703), with colour and texture features proving more transferable than spatial descriptors; cross-product transfer to geometrically distinct bread requires product-specific adaptation. The framework requiresno GPU, runs on standard CPU hardware at 4 s per image, and provides complete decision transparency traceable to physical process parameters.

Interpretable machine learning for ordinal quality grading faces a fundamental tension between model transparency and predictive performance, particularly under small-data conditions where end-to-end deep learning is unreliable and domain knowledge must compensate for limited training samples. We present a dual-target feature engineering framework for interpretable ordinal grading validated on pane Carasau, a traditional flatbread whose extreme surface variability makes it a challenging small-data benchmark for machine learning under realistic acquisition constraints. The pipeline extracts 116 handcrafted visual descriptors organised into four families—colour, texture, spatial, and hotspot—and grades the quality along two independent axes: global toasting intensity and spatial uniformity, complemented by a continuous Toasting Index for process monitoring, on a dataset of 1512 images spanning four acquisition campaigns and three product types. On the primary within-batch evaluation set Campaign 01, $N=1090$), XGBoost achieves F1 macro $=0.906$ for toast classification and $R^2=0.886$ for continuous regression, substantially outperforming two fine-tuned CNN baselines on the same evaluation set (MobileNetV2: F1 $=0.523$; EfficientNet-B0: F1 $=0.518$). Feature importance analysis reveals that colour descriptors dominate toasting prediction ($87.5\%$), whilst spatial and texture features are essential for uniformity assessment ($47.4\%$ combined), providing physically grounded explanations directly traceable to the underlying thermal process. Cross-batch generalisation on held-out campaigns is moderate for the same product (XGB F1 = 0.718, $\kappa$ = 0.703); cross-product transfer to geometrically distinct variants requires product-specific adaptation. The framework requires no GPU, runs on standard CPU hardware at 4 s per image, and provides complete decision transparency, supporting deployment without specialised hardware.