Camera traps have become an extensively utilized tool in ecological research, but the manual processing of images created by a network of camera traps rapidly becomes an overwhelming task, even for small camera trap studies. We used transfer learning to create convolutional neural network (CNN) models for identification and classification. By utilizing a small dataset with an average of 275 labeled images per species class, the model was able to distinguish between species and remove false triggers. We trained the model to detect 17 object classes with individual species identification, reaching an accuracy up to 92% and an average F1 score of 85%. Previous studies have suggested the need for thousands of images of each object class to reach results comparable to those achieved by human observers; however, we show that such accuracy can be achieved with fewer images. With transfer learning and an ongoing camera trap study, a deep learning model can be successfully created by a small camera trap study. A generalizable model produced from an unbalanced class set can be utilized to extract trap events that can later be confirmed by human processors.
Changes in DNA methylation with age are observed across the tree of life. The stereotypical nature of these changes can be modeled to produce epigenetic clocks capable of predicting biological age with unprecedented accuracy. Despite the predictive ability of epigenetic clocks, the underlying processes that produce clock signals are not resolved but are hypothesized to be rooted in stochastic processes leading to an erosion in the epigenetic landscape. Here, we test this hypothesis using a novel computational approach for measuring disorder in DNA methylation patterns across the epigenome. We find that loci comprising conventional epigenetic clocks are enriched in regions that both accumulate and lose disorder with age, suggesting a direct link between DNA methylation disorder and epigenetic clock signals. Across the murine lifespan, disorder accumulates in Polycomb Repressive Complex 2 target genes and decreases in CTCF and transcription factor binding sites, resulting in genomic hotspots of age-related epigenetic disorder. We further investigate the connections between age-related changes in disorder and epigenetic clock signals by comparing the influences of development, lifespan interventions, and cellular dedifferentiation using a series of newly developed epigenetic clocks based on regional disorder, average methylation states, and commonly used measures of entropy. We identify both common responses as well as critical differences between canonical epigenetic clocks and those based on regional disorder, demonstrating a fundamental decoupling of epigenetic aging processes. Collectively, this work identifies key linkages between epigenetic disorder and epigenetic clock signals, and simultaneously demonstrates the multifaceted nature of epigenetic aging in which stochastic processes occurring at non-random loci produce predictable outcomes.
Point 1: Camera traps have become an extensively utilized tool in ecological research, but the processing of images created by a network of camera traps rapidly becomes an overwhelming task, even for small networks. Point 2: We used transfer training to create convolutional neural network (CNN) models for identification and classification. By utilizing a small dataset with less than 10,000 labeled images the model was able to distinguish between species and remove false triggers. Point 3: We trained the model to detect 17 object classes with individual species identification, reaching an accuracy of 92%. Previous studies have suggested the need for thousands of images of each object class to reach results comparable to those achieved by human observers; however, we show that such accuracy can be achieved with fewer images. Point 4: Additionally, we suggest several alternative metrics common to computer science studies to accurately evaluate the performance of such camera trap image processing models, as well as methods to adapt the model building process to two targeted purposes.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.