A Bayesian dynamic model based on multitask learning (MTL) is developed for radar automatic target recognition (RATR) using high-resolution range profile (HRRP). The aspect-dependent HRRP sequence is modeled using a truncated stick-breaking hidden Markov model (TSB-HMM) with time-evolving transition probabilities, in which the spatial structure across range cells is described by the hidden Markov structure and the temporal dependence between HRRP samples is described by the time evolution of the transition probabilities. This framework imposes the belief that temporally proximate HRRPs are more likely to be drawn from similar HMMs, while also allowing for possible distant repetition or "innovation". In addition, as formulated the stick-breaking prior and MTL mechanism are employed to infer the number of hidden states in an HMM and learn the target-dependent states collectively for all targets. The form of the proposed hierarchical model allows efficient variational Bayesian (VB) inference, of interest for large-scale problems. To validate the formulation, example results are presented for an illustrative synthesized dataset and our main application-RATR, for which we consider the measured HRRP data. For the latter, we also make comparisons to the model with the independent state-transition statistics and some other existing statistical models for radar HRRP data.
Index Terms-Hidden Markov model (HMM), hierarchicalBayesian modeling, high-resolution range profile (HRRP), multitask learning (MTL), radar automatic target recognition (RATR), variational Bayes (VB).
A series of experiments is presented that establishes for the first time the role of some of the key design parameters of porous carbons including surface area, pore volume, and pore size on battery performance. A series of hierarchical porous carbons is used as a model system with an open, 3D, interconnected porous framework and highly controlled porosity. Specifically, carbons with surface areas ranging from ≈500–2800 m2 g−1, pore volume from ≈0.6–5 cm3 g−1, and pore size from micropores (≈1 nm) to large mesopores (≈30 nm) are synthesized and tested. At high sulfur loadings (≈80 wt% S), pore volume is more important than surface area with respect to sulfur utilization. Mesopore size, in the range tested, does not affect the sulfur utilization. No relationship between porosity and long‐term cycle life is observed. All systems fail after 200–300 cycles, which is likely due to the consumption of the LiNO3 additive over cycling. Moreover, cryo‐scanning transmission electron microscopy imaging of these carbon–sulfur composites combined with X‐ray diffraction (XRD) provides further insights into the effect of initial sulfur distribution on sulfur utilization while also revealing the inadequacy of the indirect characterization techniques alone in reliably predicting distribution of sulfur within porous carbon matrices.
Recently, egocentric activity recognition has attracted considerable attention in the pattern recognition and artificial intelligence communities because of its wide applicability in medical care, smart homes, and security monitoring. In this study, we developed and implemented a deep-learning-based hierarchical fusion framework for the recognition of egocentric activities of daily living (ADLs) in a wearable hybrid sensor system comprising motion sensors and cameras. Long short-term memory (LSTM) and a convolutional neural network are used to perform egocentric ADL recognition based on motion sensor data and photo streaming in different layers, respectively. The motion sensor data are used solely for activity classification according to motion state, while the photo stream is used for further specific activity recognition in the motion state groups. Thus, both motion sensor data and photo stream work in their most suitable classification mode to significantly reduce the negative influence of sensor differences on the fusion results. Experimental results show that the proposed method not only is more accurate than the existing direct fusion method (by up to 6%) but also avoids the time-consuming computation of optical flow in the existing method, which makes the proposed algorithm less complex and more suitable for practical application.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.