RESUMO
The study of complex behaviors is often challenging when using manual annotation due to the absence of quantifiable behavioral definitions and the subjective nature of behavioral annotation. Integration of supervised machine learning approaches mitigates some of these issues through the inclusion of accessible and explainable model interpretation. To decrease barriers to access, and with an emphasis on accessible model explainability, we developed the open-source Simple Behavioral Analysis (SimBA) platform for behavioral neuroscientists. SimBA introduces several machine learning interpretability tools, including SHapley Additive exPlanation (SHAP) scores, that aid in creating explainable and transparent behavioral classifiers. Here we show how the addition of explainability metrics allows for quantifiable comparisons of aggressive social behavior across research groups and species, reconceptualizing behavior as a sharable reagent and providing an open-source framework. We provide an open-source, graphical user interface (GUI)-driven, well-documented package to facilitate the movement toward improved automation and sharing of behavioral classification tools across laboratories.
Assuntos
Aprendizado de Máquina , Neurociências , Neurociências/métodos , Animais , Humanos , Comportamento SocialRESUMO
Electrochemical capacitors fabricated with polyaniline nanofibers are cycled 150â¯000 times with 98% capacitance retention. These devices maintain an energy density of 11.41 Wh/kg at a power density of 4000 W/kg, 64 times greater than that of an identically fabricated device based on activated carbon (0.177 Wh/kg at 4600 W/kg). For applications requiring a higher specific energy, 33.39 Wh/kg at a specific power of 600 W/kg is obtained by widening the voltage window; this device retains 93% capacitance after 10â¯000 cycles. We achieve a high cycling stability through careful device engineering paired with a renewed focus on the electrochemical processes occurring at the positive and negative electrodes during cycling.
