A5016246125- Marine animal studies overview
- DNA and Biological Computing
- Data Analysis with R
- Gene Regulatory Network Analysis
- Video Surveillance and Tracking Methods
- Species Distribution and Climate Change
- Underwater Acoustics Research
- Animal Vocal Communication and Behavior
- Water Quality Monitoring Technologies
- Domain Adaptation and Few-Shot Learning
- Wildlife Ecology and Conservation
- Scientific Computing and Data Management
- Identification and Quantification in Food
- Advanced biosensing and bioanalysis techniques
- Evolution and Genetic Dynamics
- Plant and animal studies
- Gene expression and cancer classification
- Photoreceptor and optogenetics research
Wild Salmon Center
2022
Wildlife Information Liaison Development
2017-2022
Reed College
2014-2016
Abstract Determining which species are at greatest risk, where they most vulnerable, and what the trajectories of their communities populations is critical for conservation management. Globally distributed, wide-ranging whales dolphins present a particular challenge in data collection because no single research team can record over biologically meaningful areas. Flukebook.org an open-source web platform that addresses these gaps by providing researchers with latest computational tools. It...
Inspired by natural biochemicals that perform complex information processing within living cells, we design and simulate a chemically implemented feedforward neural network, which learns novel chemical-reaction-based analogue of backpropagation. Our network is in simulated chemical system, where individual neurons are separated from each other semipermeable cell-like membranes. compartmentalized, modular allows variety topologies to be constructed the same building blocks. This brings us...
Abstract Photo identification is an important tool in the conservation management of endangered species, and recent developments artificial intelligence are revolutionizing existing workflows to identify individual animals. In 2015, National Oceanic Atmospheric Administration hosted a Kaggle data science competition automate North Atlantic right whales ( Eubalaena glacialis ). The winning algorithms developed by Deepsense.ai were able individuals with 87% accuracy using series convolutional...
Photographic-identification (photo-ID) of bottlenose dolphins using individually distinctive features on the dorsal fin is a well-established and useful tool for tracking individuals; however, this method can be labor-intensive, especially when dealing with large catalogs and/or infrequently surveyed populations. Computer vision algorithms have been developed that find in an image, characterize fin, compare to catalog known individuals generate ranking potential matches based similarity. We...
Abstract 1. Photo-identification of individual snow leopards ( Panthera uncia ) is the primary technique for density estimation species. A high volume images from multiple projects, combined with pre-existing historical catalogs, has made identifying leopard individuals within cost- and time-intensive. 2. To speed classification among a photographs, we trained evaluated image methods PIE v2 (a triplet loss network), compared PIE’s accuracy to HotSpotter algorithm SIFT based algorithm)....
It is obviously useful to think of evolved individuals in terms their adaptations, yet the task empirically classifying traits as adaptations has been claimed by some be impossible principle. I reject that claim construction, introducing a formal method test whether trait an adaptation. The presented general, intuitive, and effective at identifying while remaining agnostic about adaptive function. follows directly from notion arise variation, heritability, differential fitness evolving...
The chemical reaction network (CRN) is a widely used formalism to describe macroscopic behavior of systems. Available tools for CRN modelling and simulation require local access, installation, often involve file storage, which susceptible loss, lacks searchable structure, does not support concurrency. Furthermore, simulations are single-threaded, user interfaces non-trivial use. Therefore there significant hurdles conducting efficient collaborative research. In this paper, we introduce new...