This research explores machine learning algorithms for reservoir inflow prediction, including long short-term memory (LSTM), random forest (RF), and metaheuristic-optimized models. The impact of feature engineering techniques such as discrete wavelet transform (DWT) and XGBoost feature selection is investigated. LSTM shows promise, with LSTM-XGBoost exhibiting strong generalization from 179.81 m3/s RMSE (root mean square error) in training to 49.42 m3/s in testing. The RF-XGBoost and models incorporating DWT, like LSTM-DWT and RF-DWT, also perform well, underscoring the significance of feature engineering. Comparisons illustrate enhancements with DWT: LSTM and RF reduce training and testing RMSE substantially when using DWT. Metaheuristic models like MLP-ABC and LSSVR-PSO benefit from DWT as well, with the LSSVR-PSO-DWT model demonstrating excellent predictive accuracy, showing 133.97 m3/s RMSE in training and 47.08 m3/s RMSE in testing. This model synergistically combines LSSVR, PSO, and DWT, emerging as the top performers by effectively capturing intricate reservoir inflow patterns.

Load frequency regulation (LFR) is an indispensable scheme in planning electrical power production to provide consumers with stable, reliable and uninterrupted power. In the face of complicated power system (PS) structures with increasing and intricate power demand, new controllers that offer not only good performance, but also easy commissioning in practice are required. To this end, this research introduces an exponential PID (EXP-PID) controller as a new control scheme to ameliorate the LFR performance of PSs. This controller is simple to design and has a nonlinear feature inherited from two tunable exponential functions, which are placed in front of the PID controller and act on the error signal and its time derivative individually. To achieve the utmost performance, the EXP-PID controller\'s parameters are procured by a corrected variant of the snake optimizer (co-SO). To validate the proposed control scheme, various single-/multi-area single-/multi-source PSs favored in the area are considered as test benches. A thorough comparison with the state-of-the-art approaches is performed to disclose the true efficacy of our proposal. Among the rivals, co-SO tuned EXP-PID controller, despite its simplicity, is found to render credible and promising performance in mitigating frequency and tie-line power deviations effectively.

Anaerobic digestion (AD) has the great potential to treat organic waste and achieve remarkable results effectively. However, it is very tough to establish an accurate mechanistic model for this process. Data-driven modeling technology has opened a new door to solving this problem. While when the sample set is small, traditional data-driven modeling methods are often powerless. In this paper, an effective method is proposed for data-driven high-precision modeling in small sample scenarios. A time series generative adversarial network (TimeGAN) is first utilized to augment the original high-quality small-sample data collected during the AD methane production. A novel hybrid kernel extreme learning machine (HKELM) is then designed to form a better structure of the data-driven model, whose regularization coefficient C0 is optimized by the sparrow search algorithm (SSA). Finally, this semi-finished model (SSA-HKELM) is trained by the augmented data to form the final mathematical model (TimeGAN-SSA-HKELM) for the AD methane generation process. Comparative experiments of the methane daily production prediction error have verified the effectiveness of the method, which can be extended to other similar small sample data-driven modeling scenarios.

In this paper, a novel Moth-Flame Optimization (MFO) algorithm, namely MFO algorithm enhanced by Multiple Improvement Strategies (MISMFO) is proposed for solving parameter optimization in Multi-Kernel Support Vector Regressor (MKSVR), and the MISMFO-MKSVR model is further employed to deal with the software effort estimation problems. In MISMFO, the logistic chaotic mapping is applied to increase initial population diversity, while the mutation and flame number phased reduction mechanisms are carried out to improve the search efficiency, as well the adaptive weight adjustment mechanism is used to accelerate convergence and balance exploration and exploitation. The MISMFO model is verified on fifteen benchmark functions and CEC 2020 test set. The results show that the MISMFO has advantages over other meta-heuristic algorithms and MFO variants in terms of convergence speed and accuracy. Additionally, the MISMFO-MKSVR model is tested by simulations on five software effort datasets and the results demonstrate that the proposed model has better performance in software effort estimation problem. The Matlab code of MISMFO can be found at https://github.com/loadstar1997/MISMFO .

Fruit and vegetable freshness testing can improve the efficiency of agricultural product management, reduce resource waste and economic losses, and plays a vital role in increasing the added value of fruit and vegetable agricultural products. At present, the detection of fruit and vegetable freshness mainly relies on manual feature extraction combined with machine learning. However, manual extraction of features has the problem of poor adaptability, resulting in low efficiency in fruit and vegetable freshness detection. Although exist some studies that have introduced deep learning methods to automatically learn deep features that characterize the freshness of fruits and vegetables to cope with the diversity and variability in complex scenes. However, the performance of these studies on fruit and vegetable freshness detection needs to be further improved. Based on this, this paper proposes a novel method that fusion of different deep learning models to extract the features of fruit and vegetable images and the correlation between various areas in the image, so as to detect the freshness of fruits and vegetables more objectively and accurately. First, the image size in the dataset is resized to meet the input requirements of the deep learning model. Then, deep features characterizing the freshness of fruits and vegetables are extracted by the fused deep learning model. Finally, the parameters of the fusion model were optimized based on the detection performance of the fused deep learning model, and the performance of fruit and vegetable freshness detection was evaluated. Experimental results show that the CNN_BiLSTM deep learning model, which fusion convolutional neural network (CNN) and bidirectional long-short term memory neural network (BiLSTM), is combined with parameter optimization processing to achieve an accuracy of 97.76% in detecting the freshness of fruits and vegetables. The research results show that this method is promising to improve the performance of fruit and vegetable freshness detection.

The present paper discusses the scientific and technical problem of optimizing the design and characteristics of a new type of solid-state sensors for motion parameters on bulk acoustic waves in order to increase the signal-to-noise ratio and the detectability of an informative signal against the background of its own noise and interference. Criteria for choosing materials for structural elements, including piezoelectric transducers of the sensitive element, were identified; a corresponding numerical simulation was performed using the developed program; and experimental studies according to the suggested method were carried out to validate the obtained analytical and calculated positions. The experimental results revealed the correctness of the chosen criteria for the optimization of design parameters and characteristics, demonstrated the high correlation between the results of modeling and field studies, and, thus, confirmed the prospects of using this new type of solid-state acoustic sensors of motion parameters in the navigation and control systems of highly dynamic objects.

Locally resonant metamaterials usually have narrow bandgaps, which significantly limits their applications in realistic engineering environments. In this paper, an optimization method based on the genetic algorithm is proposed to broaden bandgaps in multi-resonant piezoelectric metamaterial through the merging of multiple separated bandgaps. Using the effective medium theory, the equivalent bending stiffness and dispersion relationship of a metamaterial plate are first obtained. Then, the criteria for determining the bandgap ranges for the two cases with and without damping are provided and analyzed. Furthermore, based on the bandgap merging phenomena, an optimization method for widening the bandgap is proposed based on the genetic algorithm. By investigating the bandgap widening effects in cases without and with damping, it is found that, when there is no damping, the bandgap can only be slightly widened; while after introducing damping into the transfer functions, the bandgap can be significantly widened by more than 200%. The bandgap widening effects are verified by comparing with finite element simulation results.

Feature detection plays a crucial role in non-target screening (NTS), requiring careful selection of algorithm parameters to minimize false positive (FP) features. In this study, a stochastic approach was employed to optimize the parameter settings of feature detection algorithms used in processing high-resolution mass spectrometry data. This approach was demonstrated using four open-source algorithms (OpenMS, SAFD, XCMS, and KPIC2) within the patRoon software platform for processing extracts from drinking water samples spiked with 46 per- and polyfluoroalkyl substances (PFAS). The designed method is based on a stochastic strategy involving random sampling from variable space and the use of Pearson correlation to assess the impact of each parameter on the number of detected suspect analytes. Using our approach, the optimized parameters led to improvement in the algorithm performance by increasing suspect hits in case of SAFD and XCMS, and reducing the total number of detected features (i.e., minimizing FP) for OpenMS. These improvements were further validated on three different drinking water samples as test dataset. The optimized parameters resulted in a lower false discovery rate (FDR%) compared to the default parameters, effectively increasing the detection of true positive features. This work also highlights the necessity of algorithm parameter optimization prior to starting the NTS to reduce the complexity of such datasets.

Data-independent acquisition (DIA) techniques such as sequential window acquisition of all theoretical mass spectra (SWATH) acquisition have emerged as the preferred strategies for proteomic analyses. Our study optimized the SWATH-DIA method using a narrow isolation window placement approach, improving its proteomic performance. We optimized the acquisition parameter combinations of narrow isolation windows with different widths (1.9 and 2.9 Da) on a ZenoTOF 7600 (Sciex); the acquired data were analyzed using DIA-NN (version 1.8.1). Narrow SWATH (nSWATH) identified 5916 and 7719 protein groups on the digested peptides, corresponding to 400 ng of protein from mouse liver and HEK293T cells, respectively, improving identification by 7.52 and 4.99%, respectively, compared to conventional SWATH. The median coefficient of variation of the quantified values was less than 6%. We further analyzed 200 ng of benchmark samples comprising peptides from known ratios ofEscherichia coli, yeast, and human peptides using nSWATH. Consequently, it achieved accuracy and precision comparable to those of conventional SWATH, identifying an average of 95,456 precursors and 9342 protein groups across three benchmark samples, representing 12.6 and 9.63% improved identification compared to conventional SWATH. The nSWATH method improved identification at various loading amounts of benchmark samples, identifying 40.7% more protein groups at 25 ng. These results demonstrate the improved performance of nSWATH, contributing to the acquisition of deeper proteomic data from complex biological samples.

An efficient method for the continuous separation of Voriconazole enantiomers was developed using sulfobutyl ether-β-cyclodextrin (SBE-β-CD) as a chiral selector in high-speed countercurrent chromatography (HSCCC) with different types. The separation was performed using a two-phase solvent system consisting of n-hexane/ethyl acetate/100 mmol/L phosphate buffer solution (pH = 3.0, containing 50 mmol/L SBE-β-CD) (1.5:0.5:2, v/v/v). A fast and predictable scale-up process was achieved using an analytical DE HSCCC instrument. The optimized parameters were subsequently applied to a preparative Tauto HSCCC instrument, resulting in consistent separation time and enantiomeric purity, with throughput boosted by a remarkable 11-fold. Preparative HSCCC successfully separated 506 mg of the racemate, delivering enantiomers exceeding 99% purity as confirmed by high-performance liquid chromatography analysis. This investigation presents an effective methodology for forecasting the HSCCC scale-up process and attaining continuous separation of chiral drugs.