Automatic recording of rare behaviors of wild animals using video bio-loggers with on-board light-weight outlier detector.

Rare behaviors displayed by wild animals can generate new hypotheses; however, observing such behaviors may be challenging. While recent technological advancements, such as bio-loggers, may assist in documenting rare behaviors, the limited running time of battery-powered bio-loggers is insufficient to record rare behaviors when employing high-cost sensors (e.g. video cameras). In this study, we propose an artificial intelligence (AI)-enabled bio-logger that automatically detects outlier readings from always-on low-cost sensors, e.g. accelerometers, indicative of rare behaviors in target animals, without supervision by researchers, subsequently activating high-cost sensors to record only these behaviors. We implemented an on-board outlier detector via knowledge distillation by building a lightweight outlier classifier supervised by a high-cost outlier behavior detector trained in an unsupervised manner. The efficacy of AI bio-loggers has been demonstrated on seabirds, where videos and sensor data captured by the bio-loggers have enabled the identification of some rare behaviors, facilitating analyses of their frequency, and potential factors underlying these behaviors. This approach offers a means of documenting previously overlooked rare behaviors, augmenting our understanding of animal behavior.

Cross-species behavior analysis with attention-based domain-adversarial deep neural networks.

Since the variables inherent to various diseases cannot be controlled directly in humans, behavioral dysfunctions have been examined in model organisms, leading to better understanding their underlying mechanisms. However, because the spatial and temporal scales of animal locomotion vary widely among species, conventional statistical analyses cannot be used to discover knowledge from the locomotion data. We propose a procedure to automatically discover locomotion features shared among animal species by means of domain-adversarial deep neural networks. Our neural network is equipped with a function which explains the meaning of segments of locomotion where the cross-species features are hidden by incorporating an attention mechanism into the neural network, regarded as a black box. It enables us to formulate a human-interpretable rule about the cross-species locomotion feature and validate it using statistical tests. We demonstrate the versatility of this procedure by identifying locomotion features shared across different species with dopamine deficiency, namely humans, mice, and worms, despite their evolutionary differences.

Deep learning-assisted comparative analysis of animal trajectories with DeepHL.

A comparative analysis of animal behavior (e.g., male vs. female groups) has been widely used to elucidate behavior specific to one group since pre-Darwinian times. However, big data generated by new sensing technologies, e.g., GPS, makes it difficult for them to contrast group differences manually. This study introduces DeepHL, a deep learning-assisted platform for the comparative analysis of animal movement data, i.e., trajectories. This software uses a deep neural network based on an attention mechanism to automatically detect segments in trajectories that are characteristic of one group. It then highlights these segments in visualized trajectories, enabling biologists to focus on these segments, and helps them reveal the underlying meaning of the highlighted segments to facilitate formulating new hypotheses. We tested the platform on a variety of trajectories of worms, insects, mice, bears, and seabirds across a scale from millimeters to hundreds of kilometers, revealing new movement features of these animals.

Machine learning enables improved runtime and precision for bio-loggers on seabirds.

Unravelling the secrets of wild animals is one of the biggest challenges in ecology, with bio-logging (i.e., the use of animal-borne loggers or bio-loggers) playing a pivotal role in tackling this challenge. Bio-logging allows us to observe many aspects of animals' lives, including their behaviours, physiology, social interactions, and external environment. However, bio-loggers have short runtimes when collecting data from resource-intensive (high-cost) sensors. This study proposes using AI on board video-loggers in order to use low-cost sensors (e.g., accelerometers) to automatically detect and record complex target behaviours that are of interest, reserving their devices' limited resources for just those moments. We demonstrate our method on bio-loggers attached to seabirds including gulls and shearwaters, where it captured target videos with 15 times the precision of a baseline periodic-sampling method. Our work will provide motivation for more widespread adoption of AI in bio-loggers, helping us to shed light onto until now hidden aspects of animals' lives.

Characterizing the microbial community involved in anaerobic digestion of lipid-rich wastewater to produce methane gas.

This study attempted to characterize the microbial community and its role in anaerobic digestion of lipid. Reactors were fed semi-continuously with three related substrates, oil and its degradation intermediates (glycerol and long chain fatty acids (LCFAs)), with a stepwise increase in organic loading rate for 90 days. Microbial community analysis using next-generation sequencing (NGS) with the MiSeq Illumina platform revealed that Anaerolineaceae was the most dominant group of bacteria in all experiments, whereas Clostridium, Desulfovibrio, Rikenellaceae, and Treponema were observed characteristically in glycerol degradation and Leptospirales, Synergistaceae, Thermobaculaceae and Syntrophaceae were seen with high abundance in LCFA and oil mineralization. Furthermore, it was discovered that Methanosaeta was the most dominant archaea. The role of these microorganisms in the methane production from oil was estimated by comparing the microbial groups in the fermentation using three substrates, and a hypothetical pathway of the methane production was proposed.

Changes in the microbial community during the acclimation process of anaerobic digestion for treatment of synthetic lipid-rich wastewater.

Changes in the microbial community were investigated during the acclimation process of anaerobic digestion while treating synthetic lipid-rich wastewater, which comprised of glucose, acetic acid, lactic acid, and soybean oil. The oil content in the synthetic wastewater was increased successively from 0% to 25% and finally to 50% of the total carbon content, to clarify the effect of substrate type change from easily degradable organic materials to lipid. The oil decomposition-associated methane production rate increased as the microorganisms acclimated to the oil and eventually levelled off around 0.76 L/d. Analysis of the microbial community using next generation 16S rRNA gene sequencing (NGS) revealed the characteristic changes of dominant microorganisms Synergistales, Anaerolineales, Actinomycetales, and Nitrospirales from the domain bacteria, and Methanobacteriales and Methanosarcinales from the domain archaea. The increase in the relative abundance of Synergistales was found to be highly correlated with the increased rate of methane production from oil.

STEFTR: A Hybrid Versatile Method for State Estimation and Feature Extraction From the Trajectory of Animal Behavior.

Animal behavior is the final and integrated output of brain activity. Thus, recording and analyzing behavior is critical to understand the underlying brain function. While recording animal behavior has become easier than ever with the development of compact and inexpensive devices, detailed behavioral data analysis requires sufficient prior knowledge and/or high content data such as video images of animal postures, which makes it difficult for most of the animal behavioral data to be efficiently analyzed. Here, we report a versatile method using a hybrid supervised/unsupervised machine learning approach for behavioral state estimation and feature extraction (STEFTR) only from low-content animal trajectory data. To demonstrate the effectiveness of the proposed method, we analyzed trajectory data of worms, fruit flies, rats, and bats in the laboratories, and penguins and flying seabirds in the wild, which were recorded with various methods and span a wide range of spatiotemporal scales-from mm to 1,000 km in space and from sub-seconds to days in time. We successfully estimated several states during behavior and comprehensively extracted characteristic features from a behavioral state and/or a specific experimental condition. Physiological and genetic experiments in worms revealed that the extracted behavioral features reflected specific neural or gene activities. Thus, our method provides a versatile and unbiased way to extract behavioral features from simple trajectory data to understand brain function.