The increasing broiler demand due to overpopulation and meat imports presents challenges in poultry farming, including management, disease control, and chicken observation in varying light conditions. To address these issues, the development of AI-based management processes is crucial, especially considering the need for detecting pathological phenomena in intensive rearing. In this study, a dataset consisting of visual and thermal images was created to capture pathological phenomena in broilers. The dataset contains 10,000 images with 50,000 annotations labeled as lethargic chickens, slipped tendons, diseased eyes, stressed (beaks open), pendulous crop, and healthy broiler. Three versions of the YOLO-based algorithm (v8, v7, and v5) were assessed, utilizing augmented thermal and visual image datasets with various augmentation methods. The aim was to develop thermal- and visual-based models for detecting broilers in complex environments, and secondarily, to classify pathological phenomena under challenging lighting conditions. After training on acknowledged pathological phenomena, the thermal YOLOv8-based model demonstrated exceptional performance, achieving the highest accuracy in object detection (mAP50 of 0.988) and classification (F1 score of 0.972). This outstanding performance makes it a reliable tool for both broiler detection and pathological phenomena classification, attributed to the use of comprehensive datasets during training and development, enabling accurate and efficient detection even in complex environmental conditions. By employing both visual- and thermal-based models for monitoring, farmers can obtain results from both thermal and visual viewpoints, ultimately enhancing the overall reliability of the monitoring process.

This paper describes the implementation of an event-based Internet robotic system to monitor water quality and feed crayfish in a shadehouse, guided by a model-based development methodology. The robotic system consists of a mobile robot to transport a water multiparameter sonde and six containers for distributing food onto the pond surface, a dispatcher unit to dispense a precise amount of food from the containers, and a computer running as a server to define, over the Internet, the feeding and monitoring schedule through a client application. The development methodology starts by making an abstract functionality model to accomplish the tasks. Next, the functionality model is described using the unified modeling language (UML) that specifies the structure and behavior of the system components. Later, the methodology translates the UML dynamic description depicted by statechart diagrams into Petri net (PN) formalism. PN models are merged and analyzed based on their behavioral properties to validate the design as a stable event-based Internet system. Following the UML and PN designs, the robotic system is implemented. Local and remote experiments were performed to show the usefulness of the robot operation via the Internet for intensive cultivation of the freshwater redclaw crayfish ( Cherax quadricarinatus ).

The classification of scientific articles aligned to Sustainable Development Goals is crucial for research institutions and universities when assessing their influence in these areas. Machine learning enables the implementation of massive text data classification tasks. The objective of this study is to apply Natural Language Processing techniques to articles from peer-reviewed journals to facilitate their classification according to the 17 Sustainable Development Goals of the 2030 Agenda. This article compares the performance of multi-label text classification models based on a proposed framework with datasets of different characteristics. Results reveal that a particular combination of a transformation method with a classifier algorithm dominates the performance results.

An open-field cultivation combined-type aquaponic system (OCAS) was developed to effectively utilize saline groundwater and prevent soil salinization while ensuring food production in drylands. To achieve the sustainable food production of the OCAS in power-scarce areas, a stand-alone photovoltaic system (PVS) for the OCAS was designed through a feasibility study of utilizing solar energy to meet its power demand. As a case study, the OCAS was established in La Paz, Baja California Sur, Mexico, with power consumption 22.72 kWh/day and annual average daily global horizontal irradiation (GHI) 6.12 kWh/m²/day, considering the 2017 meteorological data. HOMER software was employed for performance analysis and techno-economic evaluation of an appropriate PVS. Thousands PVS configurations were evaluated in terms of total net present cost (NPC) and levelized cost of energy (COE). The PVS that fulfilled the power demand and had the smallest NPC was proposed, for which the NPC and COE were calculated as $46,993 and $0.438/kWh, respectively. The relationship between its annual power supply and power demand of the OCAS was also analyzed in detail. It was found that the operation hours and the amount of power generation by the proposed PVS were 4156 h and 19,106 kWh in one year. Additionally, it was predicted that the excess power would occur almost every afternoon and reach 43% of the generated power. Therefore, the COE can be further reduced by rationally utilizing the excess power during operation.