Breakthroughs, discoveries, and DIY tips sent every weekday. It wasn't quite the eureka moment a team of scientists in Japan had set out for. Leo Uesaka, a marine biologist at the University of Tokyo, planned to study how seabirds use their legs to take flight from the ocean surface. He secured matchbox-sized cameras to the undersides of 15 streaked shearwaters (Calonectris leucomelas), a Pacific Ocean petrel species, to observe their movements. The tiny, tail-facing cameras successfully recorded information on the birds' legs.

Bio-logging is a technique involving the mounting of small lightweight video cameras and/or other data-gathering devices onto the bodies of wild animals. The systems then allow researchers to observe various aspects of that animal's life, such as its behaviors and social interactions, with minimal disturbance. However, the considerable battery life required for these high-cost bio-logging systems has proven limiting so far. "Since bio-loggers attached to small animals have to be small and lightweight, they have short runtimes and it was therefore difficult to record interesting infrequent behaviors," explains study corresponding author Takuya Maekawa. "We have developed a new AI-equipped bio-logging device that allows us to automatically detect and record the specific target behaviors of interest based on data from low-cost sensors such as accelerometers and geographic positioning systems (GPS)."

In systems of multiple agents, identifying the cause of observed agent dynamics is challenging. Often, these agents operate in diverse, non-stationary environments, where models rely on hand-crafted environment-specific features to infer influential regions in the system's surroundings. To overcome the limitations of these inflexible models, we present GP-LAPLACE, a technique for locating sources and sinks from trajectories in time-varying fields. Using Gaussian processes, we jointly infer a spatio-temporal vector field, as well as canonical vector calculus operations on that field. Notably, we do this from only agent trajectories without requiring knowledge of the environment, and also obtain a metric for denoting the significance of inferred causal features in the environment by exploiting our probabilistic method. To evaluate our approach, we apply it to both synthetic and real-world GPS data, demonstrating the applicability of our technique in the presence of multiple agents, as well as its superiority over existing methods.

We describe our first-place solution to the Animal Behavior Challenge (ABC 2018) on predicting gender of bird from its GPS trajectory. The task consisted in predicting the gender of shearwater based on how they navigate themselves across a big ocean. The trajectories are collected from GPS loggers attached on shearwaters' body, and represented as a variable-length sequence of GPS points (latitude and longitude), and associated meta-information, such as the sun azimuth, the sun elevation, the daytime, the elapsed time on each GPS location after starting the trip, the local time (date is trimmed), and the indicator of the day starting the from the trip. We used ensemble of several variants of Gradient Boosting Classifier along with Gaussian Process Classifier and Support Vector Classifier after extensive feature engineering and we ranked first out of 74 registered teams. The variants of Gradient Boosting Classifier we tried are CatBoost (Developed by Yandex), LightGBM (Developed by Microsoft), XGBoost (Developed by Distributed Machine Learning Community). Our approach could easily be adapted to other applications in which the goal is to predict a classification output from a variable-length sequence.