This paper proposes a deep learning method for intra prediction. Different from traditional methods utilizing some fixed rules, we propose using a fully connected network to learn an end-to-end ...mapping from neighboring reconstructed pixels to the current block. In the proposed method, the network is fed by multiple reference lines. Compared with traditional single line-based methods, more contextual information of the current block is utilized. For this reason, the proposed network has the potential to generate better prediction. In addition, the proposed network has good generalization ability on different bitrate settings. The model trained from a specified bitrate setting also works well on other bitrate settings. Experimental results demonstrate the effectiveness of the proposed method. When compared with high efficiency video coding reference software HM-16.9, our network can achieve an average of 3.4% bitrate saving. In particular, the average result of 4K sequences is 4.5% bitrate saving, where the maximum one is 7.4%.
Battery systems coupled to photovoltaic (PV) modules for example fulfill one major function: they locally decouple PV generation and consumption of electrical power leading to two major effects. ...First, they reduce the grid load, especially at peak times and therewith reduce the necessity of a network expansion. And second, they increase the self-consumption in households and therewith help to reduce energy expenses. For the management of PV batteries charge control strategies need to be developed to reach the goals of both the distribution system operators and the local power producer. In this work optimal control strategies regarding various optimization goals are developed on the basis of the predicted household loads and PV generation profiles using the method of dynamic programming. The resulting charge curves are compared and essential differences discussed. Finally, a multi-objective optimization shows that charge control strategies can be derived that take all optimization goals into account.
This review aimed to evaluate the impact of obesity on the onset, exacerbation, and mortality of coronavirus disease 2019 (COVID‐19); and compare the effects of different degrees of obesity. PubMed, ...EMBASE, and Web of Science were searched to find articles published between December 1, 2019, and July 27, 2020. Only observational studies with specific obesity definition were included. Literature screening and data extraction were conducted simultaneously by two researchers. A random‐effects model was used to merge the effect quantity. Sensitivity analysis, subgroup analysis, and meta‐regression analysis were used to deal with the heterogeneity among studies. Forty‐one studies with 219,543 subjects and 115,635 COVID‐19 patients were included. Subjects with obesity were more likely to have positive SARS‐CoV‐2 test results (OR = 1.50; 95% CI: 1.37–1.63, I2 = 69.2%); COVID‐19 patients with obesity had a higher incidence of hospitalization (OR = 1.54, 95% CI: 1.33–1.78, I2 = 60.9%); hospitalized COVID‐19 patients with obesity had a higher incidence of intensive care unit admission (OR = 1.48, 95% CI: 1.24–1.77, I2 = 67.5%), invasive mechanical ventilation (OR = 1.47, 95% CI: 1.31–1.65, I2 = 18.8%), and in‐hospital mortality (OR = 1.14, 95% CI: 1.04–1.26, I2 = 74.4%). A higher degree of obesity also indicated a higher risk of almost all of the above events. The region may be one of the causes of heterogeneity. Obesity could promote the occurrence of the whole course of COVID‐19. A higher degree of obesity may predict a higher risk. Further basic and clinical therapeutic research needs to be strengthened.
Melatonin is a biological hormone that plays crucial roles in stress tolerance. In this study, we investigated the effect of exogenous melatonin on abiotic stress in the tea plant. Under cold, salt ...and drought stress, increasing malondialdehyde levels and decreasing maximum photochemical efficiency of PSII were observed in tea leaves. Meanwhile, the levels of reactive oxygen species (ROS) increased significantly under abiotic stress. Interestingly, pretreatment with melatonin on leaves alleviated ROS burst, decreased malondialdehyde levels and maintain high photosynthetic efficiency. Moreover, 100 μM melatonin-pretreated tea plants showed high levels of glutathione and ascorbic acid and increased the activities of superoxide dismutase, peroxidase, catalase and ascorbate peroxidase under abiotic stress. Notably, melatonin treatments can positively up-regulate the genes (
,
,
and
) expression of antioxidant enzyme biosynthesis. Taken together, our results confirmed that melatonin protects tea plants against abiotic stress-induced damages through detoxifying ROS and regulating antioxidant systems.
An equivalent subdomain method for calculating the performance parameters of permanent magnet eddy current brakes (ECB) is presented by combining subdomain technology with a magnetic equivalent ...circuit (MEC) model. The proposed method replaces the source term in the subdomain model with an equivalent current sheet applied to the boundary of an equivalent region. The relative permeability of the equivalent region is related to design parameters rather than infinite ones and is obtained by the MEC model considering the eddy current reaction. A small prototype experimental platform is established. The validity of the proposed method is verified by the experiment and the finite element method (FEM). The results show that the braking force predicted by the method match well with those obtained by the FEM without considering the edge effect, and are slightly larger than those measured by the experiment. Considering the static edge effect, the results of the proposed method agree well with the measured values and FEM results. The method also proves to be effective in the performance prediction of the ECB with different design parameters. In addition, the limitation of the proposed method is discussed in detail.
Traditional intra prediction usually utilizes the nearest reference line to generate the predicted block when considering strong spatial correlation. However, this kind of single-line-based method ...does not always work well due to at least two issues. One is the incoherence caused by the signal noise or the texture of other objects, where this texture deviates from the inherent texture of the current block. The other reason is that the nearest reference line usually has worse reconstruction quality in block-based video coding. Due to these two issues, this paper proposes an efficient multiple-line-based intra-prediction scheme to improve coding efficiency. Besides the nearest reference line, further reference lines are also utilized. The further reference lines with a relatively higher quality can provide potentially better prediction. At the same time, the residue compensation is introduced to calibrate the prediction of boundary regions in a block when we utilize further reference lines. To speed up the encoding process, this paper designs several fast algorithms. The experimental results show that compared with HM-16.9, the proposed fast search method achieves a 2.0% bit saving on average and up to 3.7% by increasing the encoding time by 112%.
Forest fire is natural disasters that are sudden, destructive and difficult to handle and rescue, with millions of hectares of forests burned every year all over the world, causing serious ecological ...damage, loss of life and property. Therefore, timely detection and treatment of early fire is of positive and important significance for forest fire early control. The fire detection method based on image processing is one of the most important means of preventing the occurrence of large-scale forest fires at present by extracting the flame and smoke features in the image and quickly determining the location of the fire. The current deep learning-based forest fire early detection methods have problems such as high false alarm rate due to small detection targets and complex environmental background, and large number of detection model parameters. In view of this, this paper proposes a lightweight early forest fire and smoke detection method based on GS-YOLOv5. Firstly, this paper proposes a novel Super-SPPF structure to replace the SPPF structure in YOLOv5, by which the output of the feature extraction network is used as input, and the input is divided into two branches to retain more semantic information, and the GhostConv operation is performed separately to reduce the number of model parameters. The Super-SPPF structure performs the serial MaxPooling operation on one of the branches, which improves the computation speed by choosing a smaller pooling kernel, and then fuses the outputs of the two branches to reduce the false alarm rate of the detection model. Secondly, C3Ghost is utilized instead of the C3 module in YOLOv5 to further reduce the number of detection model parameters. Finally, the coordinate attention (CA) module is introduced in backbone of YOLOv5 to obtain the relationship between channels and space, which enables the network to obtain the location information of interest more accurately and further improves the detection accuracy of early fires. In this paper, a self-constructed DL-Fire dataset is used to verify the performance of the GS-YOLOv5 detection model by collecting environmental interference samples and combining them with the D-Fire dataset. The experimental results show that the detection accuracy of GS-YOLOv5 is 95.9%, and the model size is 10.58 mb. Compared with YOLOv5, false alarm rate is reduced from 12% to 6% and computational complexity is reduced from 16.0 GFlops to 12.8 GFlops by GS-YOLOv5.
One of the most important aspects in battery management systems (BMS) in electric vehicles is the state of charge (SOC) estimation. SOC needs to be accurately determined for safety and performance ...reasons but cannot be measured directly due to the flatness and hysteresis of the open circuit voltage (OCV) curve of Lithium-ion chemistries as LiFePO4. The classical approach of current integration (Coulomb counting) cannot solve the problems of accumulative error and inaccurate initial values, thus advanced estimation algorithms are applied to determine the sate of charge. In this work, three model-based state observer designs including Luenberger observer, Extended Kalman Filter (EKF) and Sigma Point Kalman Filter (SPKF) are carried out and studied. These estimation approaches are verified using measurement data acquired from commercial LiFePO4 cells. In addition, computational tests analyze the systems performances in terms of tracking accuracy, estimation robustness against temperature uncertainty, sensor drift, and convergence behavior with an initial SOC offset.
► An equivalent circuit is used to describe the characteristics of LiFePO4 batteries. ► Three different model-based algorithms are designed to estimate the battery SOC. ► The estimation approaches are verified with two typical driving profiles. ► The system robustness and the convergence behavior of SOC estimators are compared.
Traditional intra prediction methods exploit some fixed rules to generate prediction, which might not be adaptive enough to handle complicated contents. In this paper, we investigate applying deep ...neural network to improve the state-of-the-art intra prediction. Considering the characteristics of block-based video coding framework, we propose a fully connected network for intra prediction where all layers except non-linear ones are fully connected. In the proposed network, the inputs are multiple reference lines of the current block and the output is the prediction for the block. When compared with the traditional intra prediction method, the richer context of current block is exploited. For this reason, the proposed network is capable of providing more accurate prediction. Experimental results demonstrate the effectiveness of proposed network. When integrated into the HEVC reference software, the proposed method can achieve up to 3.3% bitrate saving and an average of 1.6% bitrate saving for 4K sequences.