Authors
| Filter results4 paper(s) found. |
|---|
1. Data Gator: a Provisionless Network Solution for Collecting Data from Wired and Wireless SensorsAdvances in wireless sensor technology and data collection in precision agriculture enable farmers and researchers to understand operational and environmental dynamics. These advances allow the tracking of water usage, temperature variation, soil pH, humidity, sunlight penetration, and other factors which are crucial for trend prediction and analysis. Capitalizing on this advancement, however, requires data collection infrastructure using large and varied sensor networks. Adoption and implementation... G. Wells, J. Shovic, M. Everett |
2. Explainable Neural Network Alternatives for Ai Predictions: Genetic Algorithm Quantitative Association Rule MiningNeural networks in one form or another are common precision agriculture artificial intelligence techniques for making predictions based on data. However, neural networks are computationally intensive to train and to run, and are typically “black-box” models without explainable output. This paper investigates an alternative artificial intelligence prediction technique, genetic algorithm quantitative association rule mining, which creates explainable output with impacts directly quantified... M. Everett |
3. Recovery Mechanism for Real-time Precision Agriculture Sensor Networks: a Case StudyVariable rate technologies are lagging behind other precision agriculture technologies in terms of farmer adoption, and sensor networks have been identified as a necessary step to implement these improvements. However, sensor networks face many issues in terms of cost, flexibility, and reliability. In rugged outdoor environments, it cannot be assumed that a sensor network will maintain constant connectivity to a monitoring interface, even if data is still being collected onsite. This paper presents... L. Hunt, M. Everett, J. Shovic |
4. Dimensionality Reduction and Similarity Metrics for Predicting Crop Yields in Sparse Data MicroclimatesThis study explores and develops new methodologies for predicting agricultural outcomes, such as crop yields, in microclimates characterized by sparse meteorological data. Specifically, it focuses on reducing the dimensionality in time series data as a preprocessing step to generate simpler and more explainable forecast models. Dimensionality reduction helps in managing large data sets by simplifying the information into more manageable forms without significant loss of information. We explore... L. Huender, M. Everett |