The race for automation has reached farms and agricultural fields. Many of these facilities use the Internet of Things technologies to automate processes and increase productivity. Besides, Machine Learning and Deep Learning allow performing continuous decision making based on data analysis. In this work, we fill a gap in the literature and present a novel architecture based on IoT and Machine Learning / Deep Learning technologies for the continuous assessment of agricultural crop quality. This architecture is divided into three layers that work together to gather, process, and analyze data from different sources to evaluate crop quality. In the experiments, the proposed approach based on data aggregation from different sources reaches a lower percentage error than considering only one source. In particular, the percentage error achieved by our approach in the test dataset was 6.59, while the percentage error achieved exclusively using data from sensors was 6.71.

The present paper addresses the development and use of a new potentiometric electronic tongue for both qualitative and quantitative characterization of natural mineral waters. The electronic tongue is particularly related to the conductivity and ion content of/in the water sample. The analytical system is based on six ion-selective electrodes whose membranes are formulated to provide either cationic or anionic response and considering plasticizers with different dielectric constants (bis(2-ethylhexyl) sebacate, 2-nitrophenyl octyl ether or tricresylphosphate), while keeping the polymeric matrix, i.e., poly(vinyl chloride). Notably, the absence of any ionophore in the membrane provides a general response profile, i.e., no selectivity toward any special ion, which is convenient for the realization of an effective electronic tongue. The dynamic response of the tongue toward water samples of different chemical compositions and geographical locations has been obtained. At the optimized experimental conditions, the tongue presents acceptable repeatability and reproducibility (absence of hysteresis). The principal component analysis of the final potential values observed with the six electrodes allows for the differentiation and classification of the samples according to their conductivity, which is somehow related to the mineralization. Moreover, quantitative determination of the six main ions in the water samples (i.e., chloride, nitrate, hydrogen carbonate, sulfate, sodium, calcium, and magnesium) is possible by means of a simple linear calibration (and cross-validation) model.

A potentiometric electronic tongue (ET) for the analysis of well and ditch irrigation water samples is herein proposed. The sensors’ array is composed of six ion-selective electrodes based on plasticized polymeric membranes with low selectivity profiles, i.e., the membranes do not contain any selective receptor. The sensors differ between them in the type of ion-exchanger (sensors for cations or anions) and the plasticizer used in the membrane composition, while the polymeric matrix and the preparation protocol were maintained. The potentiometric response of each sensor towards the main cations (Na⁺, K⁺, Ca²⁺, Mg²⁺) and anions (HCO₃⁻, Cl⁻, SO₄²⁻, NO₃⁻) expected in irrigation water samples was characterized, revealing a fast response time (<50 s). A total of 19 samples were analyzed with the sensor array at optimized experimental conditions, but, also, a series of complementary analytical techniques were applied to obtain the exact ion composition and conductivity to develop a trustable ET. The principal component analysis of the final potential values of the dynamic response observed with each sensor in the array allows for the differentiation between most of the samples in terms of quality. Furthermore, the ET was treated with a linear multivariate regression method for the quantitative determination of the mentioned ions in the irrigation water samples, revealing rather good prediction of Mg²⁺, Na⁺, and Cl⁻ concentrations and acceptable results for the rest of ions. Overall, the ET is a promising analytical tool for irrigation water quality, exceeding traditional characterization approaches (conductivity, salinity, pH, cations, anions, etc.) in terms of overhead costs, versatility, simplicity, and total time for data provision.

A study of the transient potential signals obtained with a cation-selective electrode based on an ion-exchanger was carried out for solutions of the following individual cations at different concentrations: H⁺, Li⁺, Na⁺, K⁺, Rb⁺, Mg²⁺, Ca²⁺, choline (Ch⁺), acetylcholine (AcCh⁺), and procaine (Pr⁺). Three different general types of transient signals were distinguished depending on the value of the selectivity coefficient of the corresponding ion. A principal component analysis (PCA) was performed on the signals, finding that the qualitative identification of the corresponding ion from the scores of two principal components is possible. The study was extended to the transient signals of solutions containing an analyte in the presence of an interfering ion. The PCA of the corresponding signal allows for the detection of the presence of interfering ions, thus avoiding biased results in the determination of the analyte. Moreover, the two principal components of the transient signals obtained for each of the ions at different concentrations allow for the construction of calibration graphs for the quantitative determination of the corresponding ion. All the transient signals obtained experimentally in this work can be reconstructed accurately from principal components and their corresponding scores.

This work introduces an advanced computer vision system designed for real-time auto-identification (Auto-ID) of loads in industrial and logistics environments, optimized through a fog computing architecture. The system monitors multiple docks in logistics warehouses, identifying pallet loads in real-time and providing feedback for efficient truck loading to prevent errors. It enhances traditional Auto-ID by incorporating pallet class classification, detection, and size estimation, utilizing foundational models, such as DINOv2, MobileNetV3, SAM, Depth Anything V2, and Depth Pro, alongside few-shot learning to generate efficient training datasets with minimal labeling effort. We propose three key innovations: (1) an embedding analysis approach for precise load classification; (2) DINOv2-based visual feature detection solutions for bounding box estimation, and (3) a depth-guided segmentation strategy for improved load isolation and measurement accuracy. Experimental results on a curated industrial dataset compiled by us demonstrate high mean average precision, with optimized trade-offs between latency and accuracy for fog computing constraints. This solutions reduces cloud dependency, supports rapid online updates, and ensures robust performance in dynamic logistics settings, making it a scalable solution for automated image labeling and load identification in industrial applications.