Rapid Prediction of Wastewater Index Using CNN Architecture and PLS Series Statistical Methods

Chemical oxygen demand (COD) is an important index to measure the degree of water pollution. In this paper, near-infrared technology is used to obtain 148 wastewater spectra to predict the COD value in wastewater. First, the partial least squares regression (PLS) model was used as the basic model. Monte Carlo cross-validation (MCCV) was used to select 25 samples out of 148 samples that did not conform to conventional statistics. Then, the interval partial least squares (iPLS) regression modeling was carried out on 123 samples, and the spectral bands were divided into 40 subintervals. The optimal subintervals are 20 and 26, and the optimal correlation coefficient of the test set (RT) is 0.58. Further, the waveband is divided into five intervals: 17, 19, 20, 22 and 26. When the number of joint intervals under each interval is three, the optimal RT is 0.71. When the number of joint subintervals is four, the optimal RT is 0.79. Finally, convolutional neural network (CNN) was used for quantitative prediction, and RT was 0.9. The results show that CNN can automatically screen the features inside the data, and the quantitative prediction effect is better than that of iPLS and synergy interval partial least squares model (SiPLS) with joint subinterval three and four, indicating that CNN can be used for quantitative analysis of water pollution degree.

A novel statistically tracked particle swarm optimization method for automatic generation control

Particle swarm optimization(PSO)is one of the popular stochastic optimization based on swarm intelligence algorithm.This simple and promising algorithm has applications in many research fields.In PSO,each particle can adjust its‘flying’according to its own flying experience and its companions’flying experience.This paper proposes a new PSO variant,called the statistically tracked PSO,which uses group statistical characteristics to update the velocity of the particle after certain iterations,thus avoiding localminima and helping particles to explore global optimum with an improved convergence.The performance of the proposed algorithm is tested on a deregulated automatic generation control problem in power systems and encouraging results are obtained.

Coal washing improvement by determination of optimal mixture of feed blends

Coals from different mines are feed in the Zirab plant without any control on weight percentage blending of them. Three major coal types of different ranks (Kiasar, Lavidj and Karmozd) were blended in various proportions to find an optimum condition in flotation circuit in Alborz Markazi coal washing plant. Flotation tests were conducted for prepared blended coal samples to assess floatability of various coal samples. In this paper, mixture design as a statistical method was used to optimize coal blend to increase recovery and grade in Zirab coal washing plant. The statistical analysis showed that the weight percent blending of different coals and interaction between Lavidj and Karmozd regions coal had significant effects on the coal recovery. The optimum condition of 95% recovery and 12% ash content could be reached with 10%, 20%, and 70% blending portion of Kiasar, Lavidj and Karmozd regions coal, respectively.

An optimal filter based MPC for systems with arbitrary disturbances

In this study, a linear model predictive control(MPC) approach with optimal filters is proposed for handling unmeasured disturbances with arbitrary statistics. Two types of optimal filters are introduced into the framework of MPC to relax the assumption of integrated white noise model in existing approaches. The introduced filters are globally optimal for linear systems with unmeasured disturbances that have unknown statistics. This enables the proposed MPC to better handle disturbances without access to disturbance statistics. As a result, the effort required for disturbance modeling can be alleviated. The proposed MPC can achieve offset-free control in the presence of asymptotically constant unmeasured disturbances. Simulation results demonstrate that the proposed approach can provide an improved disturbance ?rejection performance over conventional approaches when applied to the control of systems with unmeasured disturbances that have arbitrary statistics.

Cooperated Bayesian algorithm for distributed scheduling problem

This paper presents a new distributed Bayesian optimization algorithm(BOA)to overcome the efficiency problem when solving NP scheduling problems.The pro-posed approach integrates BOA into the co-evolutionary schema,which builds up a concurrent computing environ-ment.A new search strategy is also introduced for local op-timization process.It integrates the reinforcement learning(RL)mechanism into the BOA search processes,and then uses the mixed probability information from BOA(post-probability)and RL(pre-probability)to enhance the cooperation between different local controllers,which im-proves the optimization ability of the algorithm.The ex-periment shows that the new algorithm does better in both optimization(2.2%)and convergence(11.7%),compared with classic BOA.

Underwater moving noise source identification based on hybrid near-field acoustical holography

Near-field acoustical holography (NAH) is a powerful tool for identifying noise sources and visualizing acoustic field. By recording the acoustic pressures in the near-field, the acoustic quantities in the whole 3-D field can be reconstructed and predicted. However, the current theory of NAH is not applicable to tracking large scale moving noise sources. Therefore, the hybrid near-field acoustical holography is developed for reconstructing acoustic radiation, which is derived from statistically optimized near-field acoustical holography (SONAH) and moving frame acoustical holography (MFAH). The theoretical formulation is systematically addressed. This method enables us to visualize the noise generated by moving noise sources and the measurement array can be smaller than the source, which improves the practicability and efficiency of this technology. Numerical simulations are presented to demonstrate the advantages of hybrid NAH. Then, two experiments have been carried out with a line array of hydrophones. The results of simulations and experiments support the proposed theory, which shows the advantage of hybrid NAH in the reconstruction of an acoustic field in an underwater holographic measurement.

Analytical determination of optimal luminosity for τ mass scan

Resorting to Hessian matrix, the analytical formula is obtained to determine the optimal luminosity proportion for the experiment of τ mass scan. Comparison of numerical results indicate the consistency between the present analytical evaluation and the previous computation based on the sampling technique.

Suboptimal Auditory Dominance in Audiovisual Integration of Temporal Cues

The present study examined whether audiovisual integration of temporal stimulus features in humans can be predicted by the maximum likelihood estimation （MLE） model which is based on the weighting of unisensory cues by their relative reliabilities. In an audiovisual temporal order judgment paradigm, the reliability of the auditory signal was manipulated by Gaussian volume envelopes, introducing varying degrees of temporal uncertainty. While statistically optimal weighting according to the MLE rule was found in half of the participants, the other half consistently overweighted the auditory signal. The results are discussed in terms of a general auditory bias in time perception, interindividual differences, as well as in terms of the conditions and limits of statistically optimal multisensory integration.

Study of the data taking strategy for a high precision τ mass measurement

To achieve a high precision τ mass measurement at the high luminosity experiment BESIII,Monte Carlo simulation and sampling technique are utilized to simulate various data taking cases for single and multiparameter fits by virtue of which the optimal scheme is determined. The optimized proportion of luminosity distributed at selected points and the relation between precision and luminosity are obtained. In addition,the optimization of the fit scheme is confirmed by scrutinizing a variety of fit possibilities.

Adapting Nanotech Research as Nano-Micro Hybrids Approach Biological Complexity,A Review

Today＇s emergence of nano-micro hybrid structures with almost biological complexity is of fundamental interest. Our ability to adapt intelligently to the challenges has ramifications all the way from fundamentally changing research itself, over applications critical to future survival, to posing globally existential dangers. Touching on specific issues such as how complexity relates to the catalytic prowess of multi-metal compounds, we discuss the increasingly urgent issues in nanotechnology also very generally and guided by the motto ＇Bio Is Nature＇s Nanotech＇. Technology belongs to macro-evolution; for example integration with artificial intelligence （AI） is inevitable. Darwinian adaptation manifests as integration of complexity, and awareness of this helps in developing adaptable research methods that can find use across a wide range of research. The second half of this work reviews a diverse range of projects which all benefited from ＇playful＇ programming aimed at dealing with complexity. The main purpose of reviewing them is to show how such projects benefit from and fit in with the general, philosophical approach, proving the relevance of the ＇big picture＇ where it is usually disregarded.