We consider the problem of semi-supervised graph-based learning upon multimodal and mixmodal data. Since in semi-supervised settings, the labeled information is very limited, we first propose a non-convex sparse-coding based label propagation (α-SLP) method to estimate the soft labels, and thereby to enrich the supervised information. By considering the structural properties of multimodal and mixmodal data, we present a semi-supervised graph-based embedding (SGE) approach that incorporates the soft label information with the hierarchical local geometric information of within-class, between-class, and overall-class data. Based on this, subspaces characterizing the multimodal and mixmodal data structure can be derived by maximizing the weighted between-class separability and minimizing the locality-preserved within-class as well as overall-class distances of the training samples. We further extend SGE into semi-supervised sparse subspace learning scenarios and present an α-structural-regularization-induced SGE (α-SSGE) model, which can give better results in extracting discriminative groups of features by utilizing the non-convex structural regularization techniques. Experiments for multimodal and mixmodal digit as well as face recognition verify the validity and effectiveness of the proposed models.

BACKGROUND: Due to large dimensional matrix multiplications, the existing iterative algorithms for cone beam computed tomography (CBCT) reconstruction often face problems of heavy computational workload and large volume of memory usage. OBJECTIVE: This study proposes and tests an iterative algorithm of 3DA-TVAL3 for fast reconstruction of CBCT images using undersampled measurement data and the reduced amount of computer memories. METHODS: In order to reduce computational workload and computer memories based on the sparsity of the CBCT measurement matrix, the proposed iterative algorithm applies elementwise scalar multiplications in the iterative computation to search for optimal solution. Through a number of tests on three different CT data sets with different number of projections, the reconstruction performance of the proposed algorithm is compared with that of two accelerated iterative algorithms and the conventional FDK algorithm. RESULTS: The visual and quantitative evaluations using the normalized mean square error, peak signal to noise ratio and structural similarity metrics demonstrated the faster computational time and the higher image quality of using the proposed 3DA-TVAL3 algorithm than using other conventional algorithms under comparison. CONCLUSIONS: The proposed 3DA-TVAL3 algorithm can perform efficient and fast computation of CBCT reconstruction using the reduced amount of computer memories.

Driver drowsiness is one of main causes of road accidents worldwide and has drawn attentions of automobile industries, government organisations as well as researcher scientists and engineers. A non‐contact Doppler radar technique for monitoring driver drowsiness is presented. On the basis of unobtrusive Doppler measurement of the respiratory and heart signals, the statistical analysis shows that there is a consistent dependency of the respiratory depth on drowsiness level of drivers. It shows that the non‐contact Doppler radar technique can provide an effective approach to monitor driver drowsiness.

Direction of arrival (DOA) estimation in array processing using uniform/sparse linear arrays is concerned in this paper. While sparse methods via approximate parameter discretization have been popular in the past decade, the discretization may cause problems, e.g., modeling error and increased computations due to dense sampling. In this paper, an exact discretization-free method, named as sparse and parametric approach (SPA), is proposed for uniform and sparse linear arrays. SPA carries out parameter estimation in the continuous range based on well-established covariance fitting criteria and convex optimization. It guarantees to produce a sparse parameter estimate without discretization required by existing sparse methods. Theoretical analysis shows that the SPA parameter estimator is a large-snapshot realization of the maximum likelihood estimator and is statistically consistent (in the number of snapshots) under uncorrelated sources. Other merits of SPA include improved resolution, applicability to arbitrary number of snapshots, robustness to correlation of the sources and no requirement of user-parameters. Numerical simulations are carried out to verify our analysis and demonstrate advantages of SPA compared to existing methods.