WavNet — Visual saliency detection using Discrete Wavelet Convolutional Neural Network

In the recent advancements in image and video analysis, the detection of salient regions in the image becomes the initial step. This plays a crucial role in deciding the performance of such algorithms. In this work, a Multi-Resolution Feature Extraction (MRFE) technique that makes use of Discrete Wavelet Convolutional Neural Network (DWCNN) for generating features is employed. An Enhanced Feature Extraction (EFE) module extracts additional features from the high level features of the DWCNN, which are used to frame both channel as well as spatial attention models for yielding contextual attention maps. A new hybrid loss function is also proposed, which is a combination of Balanced Cross Entropy (BCE) loss and Edge based Structural Similarity (ESSIM) loss that effectively identifies and segments the salient regions with clear boundaries. The method is tested exhaustively with five different benchmark datasets and is proved superior to the existing state-of-the-art methods with a minimum Mean Absolute error (MAE) of 0.03 and F-measure of 0.956.     

Sub-band coding of hexagonal images

According to the circle-packing theorem, the packing efficiency of a hexagonal lattice is higher than an equivalent square tessellation. Consequently, in several contexts, hexagonally sampled images compared to their Cartesian counterparts are better at preserving information content. In this paper, novel mapping techniques alongside the wavelet compression scheme are presented for hexagonal images. Specifically, we introduce two tree-based coding schemes, referred to as SBHex (spirally-mapped branch-coding for hexagonal images) and BBHex (breadth-first block-coding for hexagonal images). Both of these coding schemes respect the geometry of the hexagonal lattice and yield better compression results. Our empirical results show that the proposed algorithms for hexagonal images produce better reconstruction quality at low bits per pixel representations compared to the tree-based coding counterparts for the Cartesian grid.     

Frequency response data-based peak filter design applied to MIMO large-scale high-precision scan stage

A large-scale high-precision scan stage is important equipment in the industrial productions of micro-fabrication such as flat panel display (FPD) lithography systems. Designing controllers for multi-input multi-output (MIMO) systems is time-consuming and needs experience because of the interaction between each axis and many controller tuning parameters. The aim of this study is to develop a peak filter design method based on frequency response data to reduce repetitive disturbance. This data-based approach does not use the model and only uses the frequency response data of the controlled system and the disturbance spectrum calculated from the scanning error data (Contribution 1). The peak filter is designed by convex optimization and satisfies robust stability conditions for six-degree-of-freedom systems (Contribution 2). The control performance of the designed peak filter is experimentally demonstrated with an industrial MIMO large-scale high-precision scan stage in reducing the scanning error of the main stroke of the translation along the $x$-axis (Contribution 3).     

Analysis of pressure and heat distribution in a dilating or contracting filter chamber with two outlets using multivariate spectral quasilinearization method

The development of efficient filters is an essential part of industrial machinery design, specifically to increase the lifespan of a machine. In the filter chamber design considered in this study, the magnetic material is placed along the horizontal surface of the filter chamber. The inside of the filter chamber is layered with a porous material to restrict the outflow of unwanted particles. This study aims to investigate the flow, pressure, and heat distribution in a dilating or contracting filter chamber with two outlets driven by injection through a permeable surface. The proposed model of the fluid dynamics within the filter chamber follows the conservation equations in the form of partial differential equations. The model equations are further reduced to a steady case through Lie's symmetry group of transformation. They are then solved using a multivariate spectral-based quasilinearization method on the Chebyshev–Gauss–Lobatto nodes. Insights and analyses of the thermophysical parameters that drive optimal outflow during the filtration process are provided through the graphs of the numerical solutions of the differential equations. We find, among other results, that expansion of the filter chamber leads to an overall decrease in internal pressure and an increase in heat distribution inside the filter chamber. The results also show that shrinking the filter chamber increases the internal momentum inside the filter, which leads to more outflow of filtrates.     

Deterministic and probabilistic ship pitch prediction using a multi-predictor integration model based on hybrid data preprocessing,reinforcement learning and improved QRNN

The deterministic and probabilistic prediction of ship motion is important for safe navigation and stable real-time operational control of ships at sea. However, the volatility and randomness of ship motion, the non-adaptive nature of single predictors and the poor coverage of quantile regression pose serious challenges to uncertainty prediction, making research in this field limited. In this paper, a multi-predictor integration model based on hybrid data preprocessing, reinforcement learning and improved quantile regression neural network (QRNN) is proposed to explore the deterministic and probabilistic prediction of ship pitch motion. To validate the performance of the proposed multi-predictor integrated prediction model, an experimental study is conducted with three sets of actual ship longitudinal motions during sea trials in the South China Sea. The experimental results indicate that the root mean square errors (RMSEs) of the proposed model of deterministic prediction are 0.0254°, 0.0359°, and 0.0188°, respectively. Taking series #2 as an example, the prediction interval coverage probabilities (PICPs) of the proposed model of probability predictions at 90%, 95%, and 99% confidence levels (CLs) are 0.9400, 0.9800, and 1.0000, respectively. This study signifies that the proposed model can provide trusted deterministic predictions and can effectively quantify the uncertainty of ship pitch motion, which has the potential to provide practical support for ship early warning systems.     

Finite-time adaptive fuzzy control for a class of output constrained nonlinear systems with dead-zone

The article investigates the finite-time adaptive fuzzy control for a class of nonlinear systems with output constraint and input dead-zone. First, by skillfully combining the barrier Lyapunov function, backstepping design method, and finite-time control theory, a novel adaptive state-feedback tracking controller is constructed, and the output constraint of the nonlinear system is not violated. Second, the fuzzy logic system is used to approximate unknown function in the nonlinear system. Third, the finite-time command filter is introduced to avoid the problem of “complexity explosion” caused by repeated differentiations of the virtual control signal in conventional backstepping control schemes. Meanwhile, a new saturation function is added in the compensating signal for filter error to improve control accuracy. Finally, based on Lyapunov stability analysis, all the signals of the closed-loop are proved to be semi-globally uniformly ultimately bounded, and the tracking error converges to a small neighborhood region of the origin in a finite time. A simulation example is presented to demonstrate the effectiveness for the proposed control scheme.     

Influence of pulse-jet cleaning pressure on performance of compact dust collector with pleated filter operated in clean-on-time mode

To operate a bag filter continuously, pulse-jet cleaning of dust particles from the filter medium is commonly required, and the pulse-jet pressure significantly affects the filter performance. In this study, the accumulation structure of residual dust particles inside and on the surface of a filter medium at different pulse-jet pressures was investigated by constructing a simple model, and the influence of the dust structure on the filter performance was clarified. Using a simple model, we determined the effective ratio of filtration area β, which represents the ratio of the filterable area to the total filtration area, the true resistance coefficient due to the primary dust layer ζ_p’ thinly deposited on the filter surface, and the true resistance coefficient inside the filter media itself ζ_f’_. The effective ratio of filtration area β decreased with operation time for all pulse-jet pressures; however, it maintained a high value when the pulse-jet pressure was high. The validity of β analyzed by the model was verified using two different methods, and the results showed good agreement, indicating that the model is effective in identifying real conditions. The true resistance coefficient due to the primary dust layer ζ_p’ decreased as the pulse-jet pressure increased; however, the true resistance coefficient inside the filter media itself ζ_f’ was the highest at 0.5 MPa. In addition, the dust collection efficiency was different at each pulse-jet pressure, which was considered to be caused by the difference in the dust particle accumulation structure.     

A Fusion Kalman Filter and UFIR Estimator Using the Influence Function Method

In this paper, the Kalman filter (KF) and the unbiased finite impulse response (UFIR) filter are fused in the discrete-time state-space to improve robustness against uncertainties. To avoid the problem where fusion filters may give up some advantages of UFIR filters by fusing based on noise statistics, we attempt to find a way to fuse without using noise statistics. The fusion filtering algorithm is derived using the influence function that provides a quantified measure for disturbances on the resulting filtering outputs and is termed as an influence finite impulse response (IFIR) filter. The main advantage of the proposed method is that the noise statistics of process noise and measurement noise are no longer required in the fusion process, showing that a critical feature of the UFIR filter is inherited. One numerical example and a practice-oriented case are given to illustrate the effectiveness of the proposed method. It is shown that the IFIR filter has adaptive performance and can automatically switch from the Kalman estimate to the UFIR estimates according to operating conditions. Moreover, the proposed method can reduce the effects of optimal horizon length on the UFIR estimate and can give the state estimates of best accuracy among all the compared methods.      

Evaluation of the localized corrosion on Mg electrode surface by electrochemical noise technique

The symmetrical and asymmetrical electrodes made of Mg were studied in 0.1-M NaCl electrolyte adjusted at pH 12. The statistical and wavelet methods were employed for analyzing the electrochemical current noise (ECN) signals. The asymmetric configuration was used for electrochemical detection of filiform corrosion on Mg electrode. The real time scale of the dominant transients of the asymmetric electrodes was detected on the basis of the maximum peak in the SDPS plots. The SDPS values of the real time scale crystals of the ECN signals resulting from asymmetrical electrodes increased with the increase in immersion time due to the onset of filiform corrosion.     

Long-term performance analysis of chemical filters in clean rooms based on a prediction model

Chemical filters are the most important devices for removing gas-phase pollutants in clean rooms. However, the testing concentration of chemical filters is too high for reflecting their performance in a real clean room environment. This study tested the adsorption performance of chemical filters in the two most commonly used shapes at different concentrations. Then, the Langmuir equation and Wheeler-Jonas kinetic equation were combined to establish an adsorption performance prediction model of chemical filters under actual conditions. The predicted values of the model were in good agreement with the experimental results, which indicated the high accuracy of the prediction model. The model does not need to test the microscopic parameters of the adsorbent and can maintain high accuracy at low concentrations. A fast method for calculating the service life of chemical filters was also presented. Based on this model, the total cost of using a chemical filter with a high carbon content in microelectronic clean rooms could be decreased by 45% due to decreasing the number of filter replacements over 3 months. So a chemical filter with a high carbon content should be preferred over a filter with low resistance in microelectronic clean rooms.