No abstract

Due to nutritional benefits and perceived humane ways of treating the animals, the demand for antibiotic-free pastured poultry chicken has continued to be steadily rise. Despite the non-usage of antibiotics in pastured poultry broiler production, antibiotic resistance (AR) is reported in zoonotic poultry pathogens. However, factors that drive multidrug resistance (MDR) in pastured poultry are not well understood. In this study, we used machine learning and deep learning approaches to predict farm management practices and physicochemical properties of feces and soil that drive MDR in zoonotic poultry pathogens. Antibiotic use in agroecosystems is known to contribute to resistance. Evaluation of the development of resistance in environments that are free of antibiotics such as the all-natural, antibiotic-free, pastured poultry production systems described here is critical to understand the background AR in the absence of any selection pressure, i.e., basal levels of resistance. We analyzed 1635 preharvest (feces and soil) samples collected from forty-two pastured poultry flocks and eleven farms in the Southeastern United States. CDC National Antimicrobial Resistance Monitoring System guidelines were used to determine antimicrobial/multidrug resistance profiles of Salmonella, Listeria, and Campylobacter. A combination of two traditional machine learning (RandomForest and XGBoost) and three deep learning (Multi-layer Perceptron, Generative Adversarial Network, and Auto-Encoder) approaches identified critical farm management practices and environmental variables that drive multidrug resistance in poultry pathogens in broiler production systems that represents background resistance. This study enumerates management practices that contribute to AR and makes recommendations to potentially mitigate multidrug resistance and the prevalence of Salmonella and Listeria in pastured poultry.

Zoonotic diseases or zoonoses are infections due to the natural transmission of pathogens between species (animals and humans). More than 70% of emerging infectious diseases are attributed to animal origin. Artificial Intelligence (AI) models have been used for studying zoonotic pathogens and the factors that contribute to their spread. The aim of this literature survey is to synthesize and analyze machine learning, and deep learning approaches applied to study zoonotic diseases to understand predictive models to help researchers identify the risk factors, and develop mitigation strategies. Based on our survey findings, machine learning and deep learning are commonly used for the prediction of both foodborne and zoonotic pathogens as well as the factors associated with the presence of the pathogens.

Rapid advancements in Cyber-Physical System (CPS) capabilities have motivated farmers to deploy this ecosystem on their farms. However, there is a growing concern among users regarding the security risks associated with CPS. Especially with rising number of cyber-attacks on CPS, such as modifying sensor readings, interrupting operations, etc. Therefore, this paper describes a security surveillance framework to detect deviations in the ecosystem by incorporating a digital twin supported anomaly detection model. The reason for incorporating digital twins is that they add value by enabling real-time monitoring of connected smart farms. We pre-process the collected data from sensors deployed on the smart farm setup. The pre-processed data is fused with our smart farm ontology to populate a knowledge graph. The generated graph is further queried to extract the necessary sensor data. We utilize the extracted normal data to train the anomaly detection model. Further, we tested our model if it identifies abnormal values from sensors by simulating anomalous use case scenarios specific to our ecosystem.

Learning the meaning of grounded languagelanguage that references a robot's physical environment and perceptual data-is an important and increasingly widely studied problem in robotics and human-robot interaction. However, with a few exceptions, research in robotics has focused on learning groundings for a single natural language pertaining to rich perceptual data. We present experiments on taking an existing natural language grounding system designed for English and applying it to a novel multilingual corpus of descriptions of objects paired with RGB-D perceptual data. We demonstrate that this specific approach transfers well to different languages, but also present possible design constraints to consider for grounded language learning systems intended for robots that will function in a variety of linguistic settings.