Corn (Zea mays L.) is one of the most sensitive crops to planting pattern and early-season uniformity. The most common method to determine number of plants is by visual inspection on the ground but this field activity becomes time-consuming, labor-intensive, biased, and may lead to less profitable decisions by farmers. The objective of this study was to develop a reliable, timely, and unbiased method for counting corn plants based on ultra-high-resolution imagery acquired from unmanned aerial systems (UAS) to automatically scout fields and applied to real field conditions. A ground sampling distance of 2.4 mm was targeted to extract information at a plant-level basis. First, an excess greenness (ExG) index was used to individualized green pixels from the background, then rows and inter-row contours were identified and extracted. A scalable training procedure was implemented using geometric descriptors as inputs of the classifier. Second, a decision tree was implemented and tested using two training modes in each site to expose the workflow to different ground conditions at the time of the aerial data acquisition. Differences in performance were due to training modes and spatial resolutions in the two sites. For an object classification task, an overall accuracy of 0.96, based on the proportion of corrected assessment of corn and non-corn objects, was obtained for local (per-site) classification, and an accuracy of 0.93 was obtained for the combined training modes. For successful model implementation, plants should have between two to three leaves when images are collected (avoiding overlapping between plants). Best workflow performance was reached at 2.4 mm resolution corresponding to 10 m of altitude (lower altitude); higher altitudes were gradually penalized. The latter was coincident with the larger number of detected green objects in the images and the effectiveness of geometry as descriptor for corn plant detection.

Purpose: Precision technologies have been available at the farm level for decades. Some technologies have been readily adopted, while the adoption of other technologies has been slower. The purpose of this study is to examine the factors influencing farmers' time-to-adoption decisions as duration between year of commercialization of precision agriculture (PA) technologies and year of adoption, at the farm level.Design/methodology/approach: Time-to-adoption, which is the difference in years between technologies becoming commercially available and the year of adoption was determined using non-parametric duration analysis, and the impact of specific farm/farmer characteristics on time-to-adoption were estimated using a semi-parametric Cox proportional-hazard (CPH) model, based on a panel dataset of 316 Kansas farms from 2002 to 2018.Findings: The findings indicate that, time-to-adoption for embodied-knowledge technologies such as automated guidance and section control were statistically shorter than for information-intensive technologies such as yield monitors, precision soil sampling and variable rate fertility. Duration was indirectly (directly) proportional to commercialization date of embodied-knowledge (information-intensive) technology. More so, time-to-adoption statistically differed among technologies within these two broad categories. Time-to-adoption varies across farm location and between both types of technologies. Millennial farmers are more likely to adopt both types of technologies sooner compared to baby boomers. Net farm income, percentage changes in debt-to-asset ratio, corn to total crop acres and machinery investment had no significant impact on the time-to-adoption for both information-intensive and embodied-knowledge technologies. On the other hand, while variations exist, time-to-adoption of PA technologies is mainly driven by location of farm, generation of farmer, number of workers, years of farming experience, total acres cropped and the cost of crop insurance.Originality/value: This study investigates how the financial position of farms, amongst other important factors might influence time-to-adoption of PA technologies. Results are useful to extension personnel and retailers for planning marketing or farm outreach programs taking into consideration that, time-to-adoption differs across regions and by specific characteristics, key amongst them: generation of farmer, number of workers, years of farming experience, total acres cropped and the cost of crop insurance.

Objectives: To summarize the development process of a national database that was designed to facilitate communication and collaboration, improve care, and create a framework for aggregate data sharing in cochlear implant (CI) research. Methods: A group of nationally represented, multidisciplinary CI providers cooperated to define a standard set of data elements to incorporate into a database built by them in association with a group of computer scientists and software designers. CI centers across the USA, then, joined the non-profit Auditory Implant Initiative to use the database for their own clinical purposes and to help contribute to the national de-identified dataset for research and analytics. Results: Approximately 12 months after the full release of the database, clinical information on 373 patients has been entered from 17 different CI centers representing 61 hearing professionals. A blend of six academic, seven private, and four non-profit CI centers participated in this phase of the data sharing network. Discussion: The adoption of a single, standardized database by 17 centers throughout the USA has begun a framework for data sharing in CI research. Future steps include (1) expanding adoption, (2) scaling the database to include more patients, (3) streamlining the legal hurdles required for adoption, and (4) integrating the database with other software platforms (e.g. electronic health records, processors). Conclusion: A standardized clinical outcomes database that is utilized by a growing network of CI centers can help strengthen research through aggregate data sharing.