Feral Swine Population Control Enabled By An Intelligent Species-specific Recognition System

Goal 1: Improve the efficacy and safety of pharmaceutical delivery systems by providing an automated dual-sensory species-specific animal recognition apparatus used for enabling access to the bait only when the targeted animal species is present.Specific Objectives:Optimize and fine-tune the design of the acoustic-based, referred to as SenseHog Ear, feral swine recognition subsystem developed and prototyped in Phase I.Integrate the optimized SenseHog Ear with the new generation bait box.Conduct an end-to-end testing of SenseHog Ear to identify any remaining design issues by exposing it to challenging scenarios e.g., animal vocalizations from species not used in the training process and those encompassing regional specificity in vocalizations.Develop, implement (hardware, firmware and software) and test the companion visual-based, referred to as SenseHog Eye, feral swine recognition system and investigate methods for feature extraction and classification for its optimal
performance.Develop, implement, and test a fusion mechanism to fuse or combine the decisions of the SenseHog Ear and Eye for confusion-free feral swine identification.Integrate the two subsystems (hardware, firmware, and software) with the new generation bait box to complete the dual-sensory feral swine recognition prototype.Conduct a comprehensive testing of SenseHog by exposing it to different types of animals and interference typical of the region where the system is intended to be deployed.Goal 2: Demonstrate that the prototyped dual-sensory animal recognition system achieves confusion-free feral swine identification in complex environments.Specific Objectives:Collect a large database of acoustic signatures and video data representing both a diverse set of feral swine vocalizations and other animals (e.g., bears) and common acoustic interference events that might occur in the baiting area jointly with collaborators at NWRC- APHIS in Fort Collins, Colorado.Design a series of
experiments using the collected database that will test the system's robustness against false positives and confusion in environments where both the targeted species and other animals are present.Demonstrate, using thorough statistical analysis, the system's performance in eliminating the risk of accidental baiting of non-targeted and indigenous species.Goal 3: Deliver a rugged, low-cost, and low-power completed SenseHog system to APHIS for extensive field testing and possible adoption by land/farm owners. Specific Objectives:Collaborate with the NWRC-APHIS to finalize the design and prototyping of the SenseHog integrated with the new generation bait box.Prepare and file a patent disclosure on the SenseHog technology.Prepare a brief operational documentation for ease of deployment and troubleshooting.Organize and host demonstrations and technical interchange events that provide opportunities for potential end-users, USDA stakeholders, and possible industry representatives to
evaluate the prototype and provide feedback to enhance the overall system.Jointly with APHIS streamline objectives for commercialization efforts needed to bring the product into early-stage trials governed by the USDA and Food and Drug Administration (FDA).