Blur is a key determinant in the perception of image quality. Generally, blur causes spread of edges, which leads to shape changes in images. Discrete orthogonal moments have been widely studied as effective shape descriptors. Intuitively, blur can be represented using discrete moments since noticeable blur affects the magnitudes of moments of an image. With this consideration, this paper presents a blind image blur evaluation algorithm based on discrete Tchebichef moments. The gradient of a blurred image is first computed to account for the shape, which is more effective for blur representation. Then the gradient image is divided into equal-size blocks and the Tchebichef moments are calculated to characterize image shape. The energy of a block is computed as the sum of squared non-DC moment values. Finally, the proposed image blur score is defined as the variance-normalized moment energy, which is computed with the guidance of a visual saliency model to adapt to the characteristic of human visual system. The performance of the proposed method is evaluated on four public image quality databases. The experimental results demonstrate that our method can produce blur scores highly consistent with subjective evaluations. It also outperforms the state-of-the-art image blur metrics and several general-purpose no-reference quality metrics.
29 July 2021 in IEEE Transactions on Systems, Man, and Cybernetics: Systems
Proximal policy optimization (PPO) is a deep reinforcement learning algorithm based on the actor–critic (AC) architecture. In the classic AC architecture, the Critic (value) network is used to estimate the value function while the Actor (policy) network optimizes the policy according to the estimated value function. The efficiency of the classic AC architecture is limited due that the policy does not directly participate in the value function update. The classic AC architecture will make the value function estimation inaccurate, which will affect the performance of the PPO algorithm. For improvement, we designed a novel AC architecture with policy feedback (AC-PF) by introducing the policy into the update process of the value function and further proposed the PPO with policy feedback (PPO-PF). For the AC-PF architecture, the policy-based expected (PBE) value function and discount reward formulas are designed by drawing inspiration from expected Sarsa. In order to enhance the sensitivity of the value function to the change of policy and to improve the accuracy of PBE value estimation at the early learning stage, we proposed a policy update method based on the clipped discount factor. Moreover, we specifically defined the loss functions of the policy network and value network to ensure that the policy update of PPO-PF satisfies the unbiased estimation of the trust region. Experiments on Atari games and control tasks show that compared to PPO, PPO-PF has faster convergence speed, higher reward, and smaller variance of reward.
Motivation: Accumulating clinical observations have indicated that microbes living in the human body are closely associated with a wide range of human noninfectious diseases, which provides promising insights into the complex disease mechanism understanding. Predicting microbe–disease associations could not only boost human disease diagnostic and prognostic, but also improve the new drug development. However, little efforts have been attempted to understand and predict human microbe–disease associations on a large scale until now. Results: In this work, we constructed a microbe-human disease association network and further developed a novel computational model of KATZ measure for Human Microbe–Disease Association prediction (KATZHMDA) based on the assumption that functionally similar microbes tend to have similar interaction and non-interaction patterns with noninfectious diseases, and vice versa. To our knowledge, KATZHMDA is the first tool for microbe–disease association prediction. The reliable prediction performance could be attributed to the use of KATZ measurement, and the introduction of Gaussian interaction profile kernel similarity for microbes and diseases. LOOCV and k-fold cross validation were implemented to evaluate the effectiveness of this novel computational model based on known microbe–disease associations obtained from HMDAD database. As a result, KATZHMDA achieved reliable performance with average AUCs of 0.8130 ± 0.0054, 0.8301 ± 0.0033 and 0.8382 in 2-fold and 5-fold cross validation and LOOCV framework, respectively. It is anticipated that KATZHMDA could be used to obtain more novel microbes associated with important noninfectious human diseases and therefore benefit drug discovery and human medical improvement. Availability and Implementation: Matlab codes and dataset explored in this work are available at http://dwz.cn/4oX5mS. Supplementary information: Supplementary data are available at Bioinformatics online.
6 May 2023 in Computer Methods and Programs in Biomedicine
To improve the accuracy of multi‐step wind power forecast, a variational mode decomposition‐long short‐term memory (VMD‐LSTM) forecast method is proposed. Firstly, the variational mode decomposition method is adopted to decompose the wind power data into three constituent modes, named as the long‐term component, the fluctuation component and the random component. Secondly, long short‐term memory network is utilised to deeply learn the characteristics of the three constituent modes. Profit from its unique forget gate and memory gate structure, the association with long‐term time series is learned to build a multi‐step forecast model. Finally, the wind power data from ELIA and NERL are used to test. The error analysis shows that the proposed method has superior performance in the multi‐step forecast and real‐time forecast.