Simultaneous Patch-Group Sparse Coding with Dual-Weighted ℓp Minimization for Image Restoration

Sparse coding (SC) models have been proven as powerful tools applied in image restoration tasks, such as patch sparse coding (PSC) and group sparse coding (GSC). However, these two kinds of SC models have their respective drawbacks. PSC tends to generate visually annoying blocking artifacts, while GSC models usually produce over-smooth effects. Moreover, conventional ℓ1 minimization-based convex regularization was usually employed as a standard scheme for estimating sparse signals, but it cannot achieve an accurate sparse solution under many realistic situations. In this paper, we propose a novel approach for image restoration via simultaneous patch-group sparse coding (SPG-SC) with dual-weighted ℓp minimization. Specifically, in contrast to existing SC-based methods, the proposed SPG-SC conducts the local sparsity and nonlocal sparse representation simultaneously. A dual-weighted ℓp minimization-based non-convex regularization is proposed to improve the sparse representation capability of the proposed SPG-SC. To make the optimization tractable, a non-convex generalized iteration shrinkage algorithm based on the alternating direction method of multipliers (ADMM) framework is developed to solve the proposed SPG-SC model. Extensive experimental results on two image restoration tasks, including image inpainting and image deblurring, demonstrate that the proposed SPG-SC outperforms many state-of-the-art algorithms in terms of both objective and perceptual quality.

Smoothing in Ordinal Regression: An Application to Sensory Data

The so-called proportional odds assumption is popular in cumulative, ordinal regression. In practice, however, such an assumption is sometimes too restrictive. For instance, when modeling the perception of boar taint on an individual level, it turns out that, at least for some subjects, the effects of predictors (androstenone and skatole) vary between response categories. For more flexible modeling, we consider the use of a ‘smooth-effects-on-response penalty’ (SERP) as a connecting link between proportional and fully non-proportional odds models, assuming that parameters of the latter vary smoothly over response categories. The usefulness of SERP is further demonstrated through a simulation study. Besides flexible and accurate modeling, SERP also enables fitting of parameters in cases where the pure, unpenalized non-proportional odds model fails to converge.

A fractional super-twisting control of electrically driven mechanical systems

The Super Twisting Control Algorithm (STA) constitutes a powerful and robust technique for control and observation problems. The structure of the STA allows inducing second-order sliding modes, such that the sliding variable and its derivative remain at zero after some finite time. However, the STA requires the strong differentiability of the sliding variable and the weak differentiability of disturbances. Thus, the sliding variable should become from an adequate design, ensuring its strong differentiability. Nonetheless, in the more general case of not necessarily integer-order differentiable disturbances, a typical case in electromechanical systems due to non-smooth effects, alternative control methods need to be considered. For that reason, this paper proposes a structural modification of the STA, allowing the integral of the discontinuous function to assume a fractional order to compensate not necessarily integer-order differentiable disturbances. An experimental assessment is conducted, and comparisons to other sliding mode based controllers are presented to demonstrate the reliability of the proposed method.

Smooth or Stepped? Laboratory Comparison of Enhanced Sonifications for Monitoring Patient Oxygen Saturation

Background: The pulse oximeter (PO) provides anesthesiologists with continuous visual and auditory information about a patient’s oxygen saturation (SpO2). However, anesthesiologists’ attention is often diverted from visual displays, and clinicians may inaccurately judge SpO2 values when relying on conventional PO auditory tones. We tested whether participants could identify SpO2 value (e.g., “97%”) better with acoustic enhancements that identified three discrete clinical ranges by either changing abruptly at two threshold values (stepped-effects) or changing incrementally with each percentage value of SpO2 (smooth-effects). Method: In all, 79 nonclinicians participated in a between-subjects experiment that compared performance of participants using the stepped-effects display with those who used the smooth-effects display. In both conditions, participants heard sequences of 72 tones whose pitch directly correlated to SpO2 value, and whose value could change incrementally. Primary outcome was percentage of responses that correctly identified the absolute SpO2 percentage, ±1, of the last pulse tone in each sequence. Results: Participants using the stepped-effects auditory tones identified absolute SpO2 percentage more accurately ( M = 53.7%) than participants using the smooth-effects tones ( M = 47.9%, p = .038). Identification of range and detection of transitions between ranges showed even stronger advantages for the stepped-effects display ( p < .005). Conclusion: The stepped-effects display has more pronounced auditory cues at SpO2 range transitions, from which participants can better infer absolute SpO2 values. Further development of a smooth-effects display for this purpose is not necessary.

A Semiparametric Sequential Ordinal Model with Applications to Analyse First Birth Intervals

A semiparametric sequential ordinal model is proposed to analyze socio-demographic and spatial determinants of first birth intervals after marriage. Random effects are introduced to capture spatially structured and unstructured latent covariates. The structured effects are modelled by assuming conditional autoregressive priors, and for the unstructured effects we use an exchangeable Gaussian prior, while the smooth effects of continuous covariatesare modelled by penalized splines. Inference is based on the mixed model approach. The model is applied to data from a cross-sectional survey. Compared to a spatial parametric predictor, the spatial semiparametric model better fits the data.

Installation Determination Method of the Combined Wind-Storage System Aiming at Smooth Effects

The energy storage system can be engaged to smooth the fluctuation output of wind power for better power quality and stability of power grid. The paper proposes a low-pass-filter-based smooth control model of the wind-storage combined system. Then the paper proposes the evaluation indices which depict power fluctuation of the combined system without/with smooth control, on which the installation storage capacity is optimized. All simulation is done on the basis of measured data