Search for: All records

While the neural commonalities as subjects perform similar task-related behaviors has been previously examined, it is very difficult to ascertain the neural commonalities for spontaneous, task-unrelated behaviors such as grooming. As our ability to record high-dimensional naturalistic behavioral and corresponding neural data increases, we can now try to understand the relationship between different subjects performing spontaneous behaviors that occur rarely in time. Here, we first apply novel machine learning techniques to behavioral video data from four head-fixed mice as they perform a self-initiated decision-making task while their neural activity is recorded using widefield calcium imaging. Across mice, we automatically identify spontaneous behaviors such as grooming and task-related behaviors such as lever pulls. Next, we explore the commonalities between the neural activity of different mice as they perform these tasks by transforming the neural activity into a common subspace, using Multidimensional Canonical Correlation Analysis (MCCA). Finally, we compare the commonalities across different trials in the same subject to those across subjects for different types of behaviors, and find that many recorded brain regions display high levels of correlation for spontaneous behaviors such as grooming. The combined behavioral and neural analysis methods in this paper provide an understanding of how similarly different animals perform innate behaviors. 

Large volumes of used electronics are often collected in remanufacturing plants, which requires disassembly before harvesting parts for reuse. Disassembly is mainly conducted manually with low productivity. Recently, human-robot collaboration is considered as a solution. For robots to assist effectively, they should observe work environments and recognize human actions accurately. Rich activity video recording and supervised learning can be used to extract insights; however, supervised learning does not allow robots to self-accomplish the learning process. This study proposes an unsupervised learning framework for achieving video-based human activity recognition. The framework consists of two main elements: a variational autoencoder-based architecture for unlabeled data representation learning, and a hidden Markov model for activity state division. The complete explicit activity classification is validated against ground truth labels; here, we use a case study of disassembling a hard disk drive. The framework shows an average recognition accuracy of 91.52% , higher than competing methods.