The use of automatic systems in the agriculture sector enhances product quality and the country’s economy. The method used to sort fruits and vegetables has a remarkable impact on the export market and quality assessment. Although manual sorting and grading can be performed easily, it is inconsistent, time-consuming, expensive, and highly influenced by the surrounding environment. In this regard, this study aimed to design and optimize the performance of a low-cost, multi-purpose, automatic RGB color-based sensor for sorting fruits. The proposed automatic color sorting system consists of hardware components including a machine frame, belt and pulleys, conveyor belt, scanning zone, plastic boxes, electric components (stepper motors, RGB color sensors, Arduino Mega, motor drivers), and software components (Arduino IDE version 2.2.1 and C++). Calibration was performed for the light intensity sensor to measure the light intensity inside the scanning zone, the conveyor speed sensor, and the RGB color sensors by testing the RGB color channels. The sensor, the height, conveyor belt color, and light intensity should be carefully adjusted to ensure a high performance of the color-based sorting system. The results showed that the appropriate sensor height ranged from 15 to 30 mm, the optimum color of the conveyor belt was black, and scanning the objects at a light intensity of 25 lux achieved the best output signals. The RGB color sensors achieved an analytical performance similar to that obtained with manual sorting without requiring the use of computers for image processing like other automatic sorting systems do in order to gather RGB data.

Fresh tomato fruits (TFs) contain a high moisture content of 90–94%, which makes storage and transportation over long distances difficult. Lately, numerous investigators have employed diverse solar dryers (SDs) in conjunction with stationary solar collectors (SCs) to dry tomatoes; however, the effectiveness of this technique is limited due to the sun’s constant motion throughout the day. Consequently, the current study set out to create an SD that is outfitted with an autonomous sun tracking system and an internet of things (IoT)-based photovoltaic system connected to an SC to continually track the sun and increase the quantity of energy absorbed. Furthermore, we investigated some operating parameters that impact the SD’s performance, taking into account three tomato slice thicknesses (STs) (4.0, 6.0, and 8.0 mm) and three air velocities (1.0, 1.5, and 2.0 m/s). The obtained data demonstrated a notable rise in the efficiency of the SD integrated with the automatic SC tracker throughout the course of the day when compared to the fixed SC, where the latter’s efficiency improved by 21.6%, indicating a strong degree of agreement. The results demonstrated a notable 20–25% reduction in drying time and a 4.9 °C increase in air temperature within the SC integrated with an automatic solar collector tracker (ASCT) at 2:00 p.m., as compared to the SC integrated with a fixed SC. The results of this study also demonstrated that there were no appreciable variations in the air speeds used to dry the tomatoes; however, the thickness of the tomato slices (TSs) had a significant impact; using 4 mm thick tomato slices resulted in a 50% reduction in drying time. Furthermore, the highest efficiency of the PV system was discovered to be 17.45%. Although the two solar dryers have very similar payback times, there are more dried tomatoes available in the markets.

The purpose of this study is to investigate how a tracking indirect solar dryer (SD) powered by photovoltaic cells affected the drying kinetics (DK) and thermo-environmental conditions of tomato slices. In this current investigation, three air speeds (1, 1.5, and 2 m/s) are used, as well as three slice thicknesses (ST) (4, 6, and 8 mm) and two SD, one of which is integrated with fixed collector motion (FCM) and another with SD tracking collector motion (TCM). The obtained results showed that the drying time (DT) isn’t significantly change with increasing air speeds from 1 to 2 m/s, this may be due to many reasons such as short DT, high temperature inside drying room, and little difference between the exanimated air speeds. When the ST is changed from 4 to 8 mm and maintaining constant air speeds, the DT for FCM and TCM rose by roughly 1.667 and 1.6 times, respectively. In addition, the drying coefficient of the TCM is higher than the FCM due to higher temperature. At 1.5 m/s air speed and 8 mm ST, the maximum values of moisture diffusivity (MD) are 7.15×10⁻¹⁰ and 9.30×10⁻¹⁰ m²/s for both FCM and TCM systems, respectively. During the study of DK, nine drying models and chose the best based on higher R² and lower χ² and RMSE are used. The findings of the DK analysis revealed that the modified two term II model fit the experimental data of various air speeds well when TF was dried using TCM and FCM systems at varying ST. These findings are based on recorded observations. Where the models’ R² values varied from 0.98005 to 0.99942 for FCM system and varied from 0.99386 to 0.99976 for TCM system. Regarding environmental analysis, it is found that the CO₂ mitigation per lifetime is ranged between 5334.9–6795.4 tons for FCM and 6305.7–6323.3 tons for TCM.

In the current study, a modified solar dryer (SD) integrated automatic solar collector tracker (ASCT) was used for drying tomato fruit (TF) at three slice thicknesses of 4, 6, and 8 mm on both drying systems at three air speeds of 1, 1.5, and 2 m/s until reaching the equilibrium moisture content. Where the comparison study was conducted between the ASCT, and another SD integrated with a fixed solar collector (FSC). The obtained results of the current study showed that the maximum solar intensity and ambient air temperature during the test period were 900 W/m², and 43.6 °C, respectively. As well as the highest efficiency of the PV system was 16.69% at the same time. On the other hand, the height, greatest diameter and smallest diameter of the TF used in the current study ranged between (4.6 and 5.2 cm), (3.5 and 4.2 cm), and (3.4 and 4.1 cm), respectively. As well as both the athematic and geometric diameters ranging between 3.87 and 4.47 cm and 2.26 and 2.38 cm, the sphericity values of tomatoes tend to have a round shape. In addition, the obtained results that there was no significant effect of the hot air velocities on the drying time, but the final moisture content (MC) decreased with increasing the hot air velocities. The lowest final MC was 6%, and it was recorded with a slice thickness of 4.0 mm that dried on SD integrated with ASCT. Additionally, color analysis showed that, the darkest tomato slices were dried on the SC integrated with FSC at a hot air velocity of 1.0 m/s. Meanwhile, the intensity of red and yellow colors significantly increased after drying with the SD integrated with ASDT. Furthermore, the chemical analysis of the dried tomato slices showed that the highest rehydration ratio of 4.43 kg water/kg dry matter was obtained for the dried tomato slices dried on SD integrated with ASCT at a hot air velocity of 1.5 m/s and a slice thickness of 8.0 mm. As well as the highest values of pH were monitored on the dried tomato slices on ASCT in comparison to the other tomato slices dried on FSC. Also, the highest ascorbic acid content recorded was 141 mg/100 g (d.b.) in tomato slices with an 8.0 mm thickness, dried using SD combined with FSC at an air velocity of 2 m/s. After drying, the total phenols content increased in all dried tomato samples but decreased with lower hot air velocities.

Recirculating Aquaculture Systems (RAS) have emerged as a sustainable approach to intensive fish production. In our previous work, we demonstrated the efficacy of a Deep Deterministic Policy Gradient (DDPG) reinforcement learning approach for optimizing feeding rates and maintaining water quality in RAS. However, the “black box” nature of deep reinforcement learning algorithms often impedes their adoption by fish farmers who lack specialized knowledge in artificial intelligence. This study addresses this gap by developing and evaluating methodologies to enhance the interpretability and explainability of DDPG-based control systems specifically for aquaculture practitioners. We employ decision tree approximation techniques to transform complex neural network policies into transparent rule-based systems while preserving performance. Our approach achieves 92.7% policy fidelity with only a 5.8% performance drop compared to the original DDPG controller. The resulting decision rules were validated with fish farmers, with 87% reporting improved understanding of system recommendations and 78% expressing increased trust in the technology. Feature importance analysis revealed dissolved oxygen, ammonia levels, and biomass as the primary decision factors. This work demonstrates how advanced artificial intelligence techniques can be made accessible to end-users through interpretable approximations, potentially accelerating the adoption of intelligent control systems in aquaculture and contributing to more sustainable food production practices.

Recirculating aquaculture systems (RAS) represent a sustainable approach to intensive fish production, but their operational complexity poses significant challenges for fish farmers. Addressing these challenges requires managing the complexity of multi-objective optimization with shifting priorities, ensuring interpretability of sophisticated AI models for practical users, and adapting control strategies to the dynamic requirements of fish development stages. This study introduces an adaptive multi-objective reinforcement learning framework that dynamically adjusts priorities across different growth stages, addressing a critical gap in current RAS management approaches. The proposed system implements a hierarchical Deep Deterministic Policy Gradient architecture with growth stage-specific policies, complemented by an interpretable visualization framework that makes complex AI decisions accessible to aquaculture practitioners. Experimental validation in a commercial-scale RAS facility with tilapia demonstrated substantial improvements in both production efficiency and system usability. Key findings include an 18.7% improvement in feed conversion ratio compared to standard implementations, while maintaining exceptional water quality stability (98.3% of time within optimal ranges). Particularly noteworthy was the system’s performance during growth phase transitions—historically challenging periods in RAS management—where adjustment time was reduced by 42.5% while maintaining stable environmental conditions. User studies revealed that the interpretable visualization components significantly enhanced farmers’ trust and understanding, with 89% of participants expressing confidence in the system compared to 65% for previous approaches. These results demonstrate how adaptive reinforcement learning with appropriate interpretability tools can bridge the gap between advanced AI techniques and practical aquaculture management, potentially accelerating adoption of intelligent control systems in commercial aquaculture.