Takuma Nakamura

Learn More
To gain insight into the functional diversity of the XTH (xyloglucan endotransglucosylase/hydrolase) gene family, we analyzed the expression profiles of two azuki bean genes, VaXTH1 and VaXTH2, which share a striking resemblance in their amino acid sequences. The two XTH genes exhibit essentially similar tissue-specific expression profiles, in that both(More)
We propose a domain-dependent/independent topic switching model based on <i>Bayesian probabilistic modeling</i> for modeling online product reviews that are accompanied with numerical ratings provided by users. In this model, each word is allocated to a domain-dependent topic or a domain-independent topic, and the distribution of topics in an online review(More)
—This paper describes the target detection and tracking architecture used by the Georgia Tech Aerial Robotics team for the American Helicopter Society (AHS) Micro Aerial Vehicle (MAV) challenge. The vision system described enables vision-aided navigation with additional abilities such as target detection and tracking all performed onboard the vehicles(More)
This paper describes a vision-based control architecture designed to enable autonomous landing on a moving platform. The landing trajectory is generated by using the receding-horizon differential dynamic programming (DDP), an optimal control method. The trajectory generation is aided by the output of a vision-based target tracking system. The vision system(More)
—Observation of an active volcano is very important to determine a strategy for estimating its eruptive activity and providing residents with an evacuation warning. However, it is too dangerous for humans to install cameras during eruptive activity to determine the status of a volcano. Furthermore, permanently installed cameras might be damaged by(More)
Infinite Hidden Markov Random Fields have been proposed for image segmentation as a solution to the problem of automatically determining the number of regions in an image; however, the model does not maintain identity of segmented regions among multiple images. In order to identify segmented regions in images, we developed Hierarchical Dirichlet Process(More)
A continuous-valued infinite relational model is proposed as a solution to the co-clustering problem which arises in matrix data or tensor data calculations. The model is a probabilistic model utilizing the framework of Bayesian Nonparametrics which can estimate the number of components in posterior distributions. The original Infinite Relational Model(More)
  • 1