Remote sensing image super-resolution has always been a major research focus, and many deep-learning-based algorithms have proposed in recent years. However, since the structure of remote images tends to be much more complex than that natural images, several difficulties still remain for super-resolution. First, it is difficult depict nonlinear mapping between high-resolution (HR) low-resolution (LR) different scenes with same model. Second, wide range scales within ground objects makes...

Summary In this study, mung bean was used as raw material to reveal the interaction mechanism between protein and polyphenols in water solution system of heat treatment speculate binding form two. Structural functional changes globulin–polyphenol complexes under different ratios conditions (70, 85 100 °C) were analysed using 2D 3D fluorescence, Fourier transform infrared spectroscopy, particle size ζ potential. The results showed that a static quenching mechanism, with mainly hydrophobic...

The timely detection and accurate location of capacitor element breakdown faults (CEBFs) are crucial in optimizing the performance alternating current (AC) filters ensuring safety stable operation high-voltage direct transmission systems. In this paper, by analyzing physical process CEBFs transient fault characteristics, a mapping relationship is established between initial phase angle fault, direction sudden changes unbalanced current, difference on low-voltage side for occurring different...

Since feeders have complicated laterals connected with unbalanced loads, the location of a ground fault is challenge in radial distribution networks. Furthermore, lower short‐circuit current due to high value resistance, which common network, will make it even more challenging identify location. Taking advantage increasing number intelligent electronic devices installed modern monitoring, and automation systems can be improved by smart feeder meters. On basis voltage information from...

The flexibility of time and location as well the availability an abundance both old new products makes online auctions important part people's daily shopping experience. Whereas many bidders rely on variants well-documented early or last-minute bidding strategies, neither strategy takes into account aspect auction competition: at any point in time, there are hundreds, even thousands, same similar items up for sale, competing bidder. In this paper, we propose a novel automated data-driven...

Operation parameters of the high-speed railway distribution system can be obtained from remote terminal units installed in box-type substations. Therefore, voltage sag profiles may utilized for fault location. This paper proposes a novel strategy location by measured data existing The proposed method makes use difference between calculated and at end lines to locate fault. Assuming that occurs any possible substations along lines, faulted line section is identified with defined sequence,...

In this paper, a spatial parallel mechanism with five degrees of freedom is studied in order to provide promising dynamic model for the control design. According inverse kinematics mechanism, derived by using Lagrangian method, and co-simulation MSC ADAMS MATLAB/Simulink adopted verify established model. Then pre-trained deep neural network (DNN) introduced predict real-time state end-effector mechanism. Compared traditional Newton’s DNN method reduces cost forward calculation while ensuring...

The self-assembled structures of coix seeds affected the enzymatic efficiency and doesn't facilitate release more active peptides. influence heating combined with ultrasound pretreatment (HT + US) on structure, properties hydrolysates (CHPs) seed prolamin was investigated. Results showed that structural prolamins has changed after HT US, including increased surface hydrophobicity, reduced α-helix random coil content, a decrease in particle size. So that, leads to changes thermodynamic...

SVM has been given top consideration for addressing the challenging problem of data imbalance learning. Here,we conduct an empirical classification analysis new UCI datasets that have dierent ratios, sizes andcomplexities. The experimentation consists comparing results with two other popularclassifiers, Naive Bayes and decision tree C4.5, to explore their pros cons. To make comparative exper-iments more comprehensive a better idea about learning performance each classifier, we employin total...

An adaptive vibration isolation system is proposed in this paper to combine the advantages of both linear and nonlinear isolators. Because structural piecewise characteristics for different levels response, stiffness damping properties could be designed according performances. The are achieved by joined utilization symmetrical precompression triangle-like structure (TLS) column frame with cam. In order design control mechanism optimum parameters, performances analyzed using averaging method...

With the development and innovation of machine learning deep technology, more fields try to apply artificial intelligence practical scenarios. We use model assist judgment preliminary case results. In this paper, we analyze basic description case, predict results from three aspects: penalty, accusation legal provisions. On one hand, forecasting can help judges lawyers make decisions, on other it also non-legal professionals have a understanding case.

In this article, a model-free controller is proposed to suppress residual vibration caused by the linkage flexibility after positioning process. The designed release potential energy rapidly repeating sequence comprising two steps. first step, acts as damper absorb deformation energy, whereas in second neural network control introduced for purpose of returning target position smoothly. simple, and only required feedback signal from motor encoder. error proved converge zero within small...

This paper proposes a novel Continuously Adjustable Magnetic-valve Controllable Reactor (CAMCR), which can avoid the control "blind area" of conventional (MCR) and reduce output harmonics MCR. There are circular truncated cones in iron cores CAMCR. Each section core saturates at different time creates current phases, i.e. phase shifted each other total reduced greatly. The mathematical model magnetization curve distribution deduced according to its geometry characteristics. simulation...