Digital currency price prediction is vital to both sellers and purchasers. Over these years, decomposition and integration models have been applied more and more to realize the goal of precise prediction, however, many of them tend to neglect the reconstruction of features or the residual series. Altogether, one of the biggest drawbacks of the decomposition and integration framework is the method applied requires manual parameter setting whether it is for decomposition or integration. Still, for the results, they are merely satisfied with the point prediction which brings high uncertainty. In this paper, an optimized feature reconstruction decomposition and two-step nonlinear integration method is proposed which gives consideration to feature reconstruction, nonlinear integration, optimization and interval prediction. The original data series is decomposed through improved variational mode decomposition based approximate entropy feature reconstruction system. Then, improved particle swarm optimization-gated recurrent unit (iPSO-GRU) is utilized in the first and second nonlinear integration part separately. Meanwhile, the residual series is given attention, if it is not a white noise series, the residual will be the input of iPSO-GRU whose result will be added back to the second integration result to form the point prediction result. Based on the point prediction result, interval prediction estimate will be generated as well via maximum likelihood function. This study chooses three kinds of digital currency as cases and the results show that the MAPE values of point prediction are all below 3.5%, and CP values of interval prediction are all 1 with suitable MWP. In addition, compared with other benchmark models, the proposed model shows better performance.
Wireless Personal Communications - As a rich clean and environmentally friendly renewable resources, wind energy has emerged as a strategic choice for countries around the world. Because the... 相似文献
Functional electrical devices have promising potentials in structural health monitoring system, human‐friendly wearable interactive system, smart robotics, and even future multifunctional intelligent room. Here, a low‐cost fabrication strategy to efficiently construct highly sensitive graphite‐based strain sensors by pencil‐trace drawn on flexible printing papers is reported. The strain sensors can be operated at only two batteries voltage of 3 V, and can be applied to variously monitoring microstructural changes and human motions with fast response/relaxation times of 110 ms, a high gauge factor (GF) of 536.6, and high stability >10 000 bending–unbending cycles. Through investigation of service behaviors of the sensors, it is found that the microcracks occur on the surface of the pencil‐trace and have a major influence on the functions of the strain sensors. These performances of the strain sensor attain and even surpass the properties of recent strain sensing devices with subtle design of materials and device architectures. The pen‐on‐paper (PoP) approach may further develop portable, environmentally friendly, and economical lab‐on‐paper applications and offer a valuable method to fabricate other multifunctional devices. 相似文献
The electrochemiluminescence (ECL) system based on the ruthenium complex has become a powerful tool in the field of analytical chemistry. However, the non‐aqueous ECL luminescence system, which does not involve complex nano‐modification, has not been widely used for the determination of analytes. In this study, N ‐methyl pyrrolidone was selected as the solvent, and it could also act as a co‐reactant of . Based on this, a simple ECL system without nanomaterials was established. Strong ECL was generated. Furthermore, a quenching effect between the excited state of and sulphamethoxazole (SMZ) was observed. Based on this, a sensitive ECL sensor for detecting SMZ is constructed. A linear relationship between ECL signal quenching intensity (ΔI) and the logarithm of SMZ concentration (log C) in the concentration range of 1 × 10−7 –1 × 10−5 mol/l is obtained. The limit of detection is as low as 3.33 × 10−9 mol/l. The method has been applied to the detection of SMZ in tap water samples with different concentration levels with satisfactory results, and the recovery was 95.3–102.6%.Inspec keywords: biosensors, electrochemical sensors, electroluminescence, chemiluminescence, organic compounds, electrochemistryOther keywords: ruthenium complex, analytical chemistry, nonaqueous ECL luminescence system, complex nanomodification, quenching effect, ECL signal quenching intensity, ECL sensor system, nanofree electrochemiluminescence biosensor system, sulphamethoxazole detection, tris(2,2′‐bipyridyl)ruthenium(II), N‐methyl pyrrolidone recognition, analyte determination, nanomaterials, SMZ concentration detection相似文献