Least Squares Support Vector Machine Research Articles

A hybrid optimized model for predicting evapotranspiration in early and late rice based on a categorical regression tree combination of key influencing factors

Crop evapotranspiration (ETC) is an important component of the agricultural hydrological cycle, and its accurate estimation is important for assessing the hydrological environment of farmlands and guiding crop irrigation. To improve the prediction accuracy of ETC for early and late rice, this study analyzed the importance of the influencing factors based on a categorical regression tree (CART) machine learning algorithm. Based on the importance results of the influencing factors obtained from CART analysis, different combinations of input factors were constructed, and daily ETC prediction models were developed for early and late rice using the least squares support vector machine (LSSVM). A three-element heuristic optimization algorithm, Sine Cosine Algorithm (SCA), Slime Mold Algorithm (SMA), and Sparrow Search Algorithm (SSA), were used to optimize the ETC model to improve the performance of the early and late rice ETC prediction models. The results of this study revealed that the strongest correlation between early and late rice ETC was net solar radiation (Rn), with importance of 0.830 and 0.802, respectively. The next strongest correlations were temperature (T), wind speed (u), soil moisture (SM) and u, leaf area index (LAI), SM (0.092, 0.02, 0.014 and 0.058, 0.049, 0.034), respectively. The accuracy of the model tended to increase as the number of influencing factors in the input combinations constructed based on the importance results increased. The accuracy of the model increased more rapidly when the input factors were one to four and the accuracy of the model increased slightly when the input factors were more than four. The SSA-LSSVM model with four-factor combinations of inputs was the least-factor combination with guaranteed model accuracy of RMSE = 0.514 mm/d, R2 = 0.924, KGE = 0.565, WI = 0.978,and MAE = 0.414 mm/d; RMSE = 0.468 mm/d, R2 = 0.910, KGE = 0.670, WI = 0.985, and MAE = 0.368 mm/d. This study may provide a reference for the prediction of evapotranspiration as a key factor in the study of the agricultural hydrological environment of early and late rice.

A novel short-term wind speed prediction method based on hybrid statistical-artificial intelligence model with empirical wavelet transform and hyperparameter optimization

The short-term wind speed prediction is important for the connection of wind power to the grid. However, it is challenging due to the stochastic and intermittent characteristics of wind speed. In this paper, a novel wind speed prediction method named as EWT-ARIMA-LSSVM-GPR-DE-GWO method is proposed, where the empirical wavelet transform (EWT) is applied to decompose the original wind speed signal into multiple intrinsic mode functions (IMF), and various prediction models including the statistical model of autoregressive integrated moving average (ARIMA), artificial intelligence models of least squares support vector machine (LSSVM) and Gaussian process regression (GPR) are used for predicting the IMF in sequence from low frequency to high frequency based on the superiority of each model. Differential evolution-grey wolf optimizer (DE-GWO) algorithm is used to optimize the hyperparameters of artificial intelligence prediction models of LSSVM and GPR. The proposed short-term wind speed prediction method shows superior performance in both accuracy and stability with validation by the measurement data. Both the EWT signal decomposition and DE-GWO hyperparameter optimization are effective to promote the prediction accuracy for wind speeds with large non-stationary.

Modeling medium resolution evapotranspiration using downscaling techniques in north-western part of India

The present investigation provides a modeling solution to downscale MODIS-based evapotranspiration (ET) at a 30 m spatial resolution from its original 500 m spatial resolution using meteorological and Landsat 8 (Operational Land Imager, OLI) data by employing downscaling models. The nine indices namely Surface Albedo, Land Surface Temperature (LST), Normalized Difference Vegetation Index (NDVI), Soil-Adjusted Vegetation Index (SAVI), Modified Soil-Adjusted Vegetation Index (MSAVI), Normalized Difference Built-up Index (NDBI), Normalized Difference Water Index (NDWI), Normalized Difference Moisture Index (NDMI), and Normalized Difference Infrared Index for Band 7 (NDIIB7) were calculated from Lansat 8 data at 30 m spatial resolution. The multiple linear regression (MLR) and Least Square Support Vector Machine (LS-SVM) models were developed to generate the relationship between MODIS 500 m ET and Landsat indices at 500 m scale. Further, these develop models were used to estimate 30 m ET based on 30 m Landsat 8 indices. The performance of developed models (MLR and LS-SVM) was carried out using correlation coefficient (CC), Nash-Sutcliffe coefficient (NASH) efficiency, Root Mean Square Error (RMSE) and Normalised Mean Square Error (NMSE). Penman–Monteith (PM) method was used to estimate the ET using observed station data. The results show that lowest ETO was observed in the month of December while it was maximum in the month of May. Using the performances indices, it was found that LS-SVM model slightly outperformed than MLR model. However, the downscaled model overestimates ET in comparison to the Penman-Monteith method. Further, the significant correlation was found between MODIS ET and LS-SVM ET at all the stations.

Variational eligibility trace meta-reinforcement recurrent network for residual life prediction of space rolling bearings

Traditional sequence recurrent neural networks (SRNNs) have the defect of long time dependence in the prediction of time series, resulting in their poor generalization ability. Moreover, it is required to traverse the whole training data set to realize supervised learning by SRNNs, which increases the time complexity and leads to their low prediction accuracy and high computation cost in the residual life prediction of space rolling bearings in the ground simulated space environment. In view of this, a novel SRNN named variational eligibility trace meta-reinforcement recurrent network (VETMRRN) is proposed for achieving higher residual life prediction accuracy and lower computation cost. In the proposed VETMRRN, a new sequence recurrent network structure is constructed to increase the memory amount of historical information, thus improving the long-term memory capacity of VETMRRN. Then, a hyperparameter self-initialization meta-learning network with an oracle gate mechanism is designed to self-initialize the hyperparameters of VETMRRN for fast determination of the optimal review sequence length. Hence, VETMRRN can adapt to different input sequence lengths and avoid the defect of long time dependence of traditional SRNNs. Furthermore, a variational auto-encoding meta policy gradient learning algorithm with an eligibility trace operator is designed to improve the training speed and enhance the global optimization effect for VETMRRN parameters. Based on the above advantages of VETMRRN, a new residual life prediction method of space rolling bearings in the ground simulated space environment is proposed. Firstly, the time-frequency fusion features are extracted by Shapely-value feature fusion from the vibration acceleration data of space rolling bearing as the performance degradation features. Then, the performance degradation features are input into VETMRRN to predict the performance degradation feature trends of space rolling bearings. Finally, a Weibull-distribution reliability model is established based on the performance degradation feature trend values to predict the residual life of space rolling bearings. The effectiveness of the proposed VETMRRN-based prediction method is verified by the vibration acceleration data collected from the self-built vibration monitoring platform of space rolling bearings in the ground simulated space environment. The results indicate that compared to traditional SRNNs, deep sparse auto-encoding neural network (DSAE-NN), and multi-kernel least-square support vector machine (MK-LSSVM), the proposed method can improve the prediction accuracy and reduce the computation cost in the residual life prediction of space rolling bearings. In the future, the generalization performance of VETMRRN still needs to be further improved.

Development and Optimization of a Novel Soft Sensor Modeling Method for Fermentation Process of Pichia pastoris.

This paper introduces a novel soft sensor modeling method based on BDA-IPSO-LSSVM designed to address the issue of model failure caused by varying fermentation data distributions resulting from different operating conditions during the fermentation of different batches of Pichia pastoris. First, the problem of significant differences in data distribution among different batches of the fermentation process is addressed by adopting the balanced distribution adaptation (BDA) method from transfer learning. This method reduces the data distribution differences among batches of the fermentation process, while the fuzzy set concept is employed to improve the BDA method by transforming the classification problem into a regression prediction problem for the fermentation process. Second, the soft sensor model for the fermentation process is developed using the least squares support vector machine (LSSVM). The model parameters are optimized by an improved particle swarm optimization (IPSO) algorithm based on individual differences. Finally, the data obtained from the Pichia pastoris fermentation experiment are used for simulation, and the developed soft sensor model is applied to predict the cell concentration and product concentration during the fermentation process of Pichia pastoris. Simulation results demonstrate that the IPSO algorithm has good convergence performance and optimization performance compared with other algorithms. The improved BDA algorithm can make the soft sensor model adapt to different operating conditions, and the proposed soft sensor method outperforms existing methods, exhibiting higher prediction accuracy and the ability to accurately predict the fermentation process of Pichia pastoris under different operating conditions.

Hybrid modeling of mechanical properties and hardness of aluminum alloy 5083 and C100 Copper with various machine learning algorithms in friction stir welding

Knowledge of mechanical properties and hardness is essential for the cost-effective and efficient friction stir welding (FSW) in producing Cu and Al composites. Correct process management requires knowledge of consistent model predictions. Many factors affect the mechanical properties and hardness, which include pin geometry, forward speed, rotational speed, and pin angle. The purpose of this research is to investigate the use of Relevance Vector Machine (RVM), Support Vector Machine (SVM), and Least Square Support Vector Machine (LSSVM) algorithms in hybrid modeling of the mechanical properties and hardness in FSW. Then, the resulting mechanical properties are modeled to three modeling methods: the hybrid LSSVM-RVM, hybrid SVM-RVM, and hybrid SVM-LSSVM. A comparison between the experimental data and the output of these models were made. R2, RMSE, and RMSE/ymax statistical indices was used in this research. The values ​​of R2 for the results of the tensile test and hardness area were obtained as 0.9712 and 0.9126, respectively. The results showed that the hybrid LSSVM-RVM model could efficiently estimate the mechanical and hardness properties.

Machine learning-assisted correlations of heat/mass transfer and pressure drop of microchannel membrane-based desorber/absorber for compact absorption cycles

Microchannel membrane-based desorbers and absorbers are key components in efficient and compact absorption refrigeration systems. To improve the accuracy of current empirical correlations for describing the heat/mass transfer and solution pressure drop characteristics, more advanced correlation models are urgently needed. This study applies three machine learning algorithms, namely Random Forest (RF), Least-Squares Support Vector Machine (LS-SVM), and Genetic Algorithm-optimized Back Propagation Artificial Neural Network (GABPNN), to develop new models for Nusselt number (Nu), Sherwood number (Sh), and friction factor (Fr) of microchannel membrane-based desorber and absorber, respectively, based on experimental results. These machine learning-assisted models effectively improve the prediction accuracy for both the desorber and absorber. Among them, the Random Forest model performs best, improving the prediction accuracy by 12.37% (Nu), 21.49% (Sh), and 14.24% (Fr) for the desorber and 24.28% (Nu), 27.82% (Sh), and 30.47% (Fr) for the absorber, compared to the conventional empirical correlations. Moreover, in relative to the correlations obtained from the literature, the Random Forest model predicts the overall heat transfer coefficient (U), sorption rate (J), and solution pressure drop (DP) with accuracies higher by 44.75%, 64.66%, and 83.52% for the desorber, and 79.66%, 81.52%, and 69.53% for the absorber. This study is expected to facilitate the simulation, design, and optimization of microchannel membrane-based desorbers/absorbers towards more efficient and compact absorption cycles.

Prediction of fat content in salmon fillets based on hyperspectral imaging and residual attention convolution neural network

The fat content of salmon is an essential indicator to evaluate its quality, and is related to its commercial value. An attention residual convolutional neural network (CNN), namely RACNN, which added channel attention and residual modules to the traditional CNN structure, was proposed to combine near-infrared hyperspectral imaging (NIR-HSI) (900-1700 nm) to predict fat contents in salmon fillets. Partial least squares regression (PLSR), least squares support vector machine (LSSVM) and CNN models were compared with the proposed RACNN models. Various spectrum preprocessing methods were used at the time. And Three feature extraction algorithms (successive projections algorithm (SPA), uninformative variable elimination (UVE), and competitive adaptive reweighted sampling (CARS)) were used to extract the effective wavelengths from the preprocessed NIR spectra. The experimental results showed that, the optimal PLSR and LSSVM models obtained coefficient of determination of prediction (Rp2) values of 0.8781 and 0.8952, respectively. The RACNN model based on full spectrum gained the highest prediction accuracies with Rp2 = 0.9033, root mean square error of prediction (RMSEP) = 1.5143, and residual predictive deviation (RPD) = 3.2707. Therefore, the proposed RACNN model enables the rapid, non-destructive and accurate prediction of the fat content in salmon fillets without additional processing on raw spectra.

Deep electron cloud‐activity and field‐activity relationships

AbstractChemists have been pursuing general mathematical laws to explain and predict molecular properties for a long time. However, most of the traditional quantitative structure‐activity relationship (QSAR) models have limited application domains; for example, they tend to have poor generalization performance when applied to molecules with parent structures different from those of the trained molecules. This paper attempts to develop a new QSAR method that is theoretically possible to predict various properties of molecules with diverse structures. The proposed deep electron cloud‐activity relationships (DECAR) and deep field‐activity relationships (DFAR) methods consist of three essentials: (1) a large number of molecule entities with activity data as training objects and responses; (2) three‐dimensional electron cloud density (ECD) or related field data by the accurate density functional theory methods as input descriptors; and (3) a deep learning model that is sufficiently flexible and powerful to learn the large data described above. DECAR and DFAR are used to distinguish 977 sweet and 1965 non‐sweet molecules (with 6‐fold data augmentation), and the classification performance is demonstrated to be significantly better than the traditional least squares support vector machine (LS‐SVM) models using traditional descriptors. DECAR and DFAR would provide a possible way to establish a widely applicable, cumulative, and shareable artificial intelligence‐driven QSAR system. They are likely to promote the development of an interactive platform to collect and share the accurate ECD and field data of millions of molecules with annotated activities. With enough input data, we envision the appearance of several deep networks trained for various molecular activities. Finally, we could anticipate a single DECAR or DFAR network to learn and infer various properties of interest for chemical molecules, which will become an open and shared learning and inference tool for chemists.

Efficient strategies for finger movement classification using surface electromyogram signals.

One of the famous research areas in biomedical engineering and pattern recognition is finger movement classification. For hand and finger gesture recognition, the most widely used signals are the surface electromyogram (sEMG) signals. With the help of sEMG signals, four proposed techniques of finger movement classification are presented in this work. The first technique proposed is a dynamic graph construction and graph entropy-based classification of sEMG signals. The second technique proposed encompasses the ideas of dimensionality reduction utilizing local tangent space alignment (LTSA) and local linear co-ordination (LLC) with evolutionary algorithms (EA), Bayesian belief networks (BBN), extreme learning machines (ELM), and a hybrid model called EA-BBN-ELM was developed for the classification of sEMG signals. The third technique proposed utilizes the ideas of differential entropy (DE), higher-order fuzzy cognitive maps (HFCM), empirical wavelet transformation (EWT), and another hybrid model with DE-FCM-EWT and machine learning classifiers was developed for the classification of sEMG signals. The fourth technique proposed uses the ideas of local mean decomposition (LMD) and fuzzy C-means clustering along with a combined kernel least squares support vector machine (LS-SVM) classifier. The best classification accuracy results (of 98.5%) were obtained using the LMD-fuzzy C-means clustering technique classified with a combined kernel LS-SVM model. The second-best classification accuracy (of 98.21%) was obtained using the DE-FCM-EWT hybrid model with SVM classifier. The third best classification accuracy (of 97.57%) was obtained using the LTSA-based EA-BBN-ELM model.

Non-destructive detection of polysaccharides and moisture in Ganoderma lucidum using near-infrared spectroscopy and machine learning algorithm

Ganoderma lucidum, the fruiting body of the Poraceae fungi G. lucidum or Ganoderma sinense, has a long history of use in promoting health and longevity in Asian countries. However, traditional methods for detecting polysaccharides and moisture in G. lucidum are complicated, time-consuming, and damaging (to the sample). In this study, rapid and nondestructive near-infrared (NIR) spectroscopy (700–2500 nm) was uesd to directly scan the back of the G. lucidum cap without powdering. Thereafter, we used synergy interval partial least squares to select the performing band and the ant lion optimization (ALO) algorithm to optimize the least squares support vector machine (LSSVM) model for these two components. The results showed that the ALO-LSSVM model could predict the total polysaccharide and moisture content with high accuracy. The correlation coefficient for calibration were both >0.9 and their ratio of prediction to deviation (RPD) values of prediction were 2.6 and 3.6, respectively, indicating the non-destructive determination of polysaccharides and moisture in G. lucidum will provide great convenience for on-site testing by procurement personnel. This shows the combination of NIR spectroscopy and the ALO-LSSVM algorithm has potential applications for the rapid and nondestructive analysis of natural products.

Assessment of protein content and insect infestation of maize seeds based on on-line near-infrared spectroscopy and machine learning

Maize is one of the most important crops in the world. The protein content and insect infestation significantly influence seed vigor and growth. Therefore, it is vital to detect the protein content and insect infestation seeds rapidly and non-destructively. In this study, a near-infrared (NIR) spectra acquisition device (900–1700 nm) was designed and employed for on-line seed quality detection. Support vector machine (SVM), logistic regression (LR), and partial least square regression discrimination analysis (PLS-DA) were used for insect infestation seeds classification. PLS and least squares-support vector machine (LS-SVM) were adopted for protein detection. Competitive adaptive reweighted sampling (CARS) and successive projections algorithm (SPA) were applied to select the feature wavelengths to reduce the redundant data and identify important information. As for insect infestation seeds, CARS-SPA-LR model achieved the classification using only 7 features with an accuracy of 0.83. In terms of protein prediction, the LS-SVM models obtained the best results for grain protein content (GPC, %) and absolute GPC (Ab_GPC, mg/kernel), respectively. The optimal models only used 22 and 21 feature wavelengths selected by CARS-SPA, with the RMSEP of 3.38 % and 2.38 mg/kernel, and RPD was 2.08 and 2.11, respectively. The results indicated that the NIR on-line acquisition system could be applied for qualitative and quantitative analysis of maize seeds.

Modeling reference evapotranspiration using machine learning and remote sensing techniques for semi-arid subtropical climate of Indian Punjab

Abstract A study was carried out to develop and evaluate the performance of different machine learning (ML) models for predicting reference evapotranspiration (ET0). The models included multiple linear regression (MLR), least square-support vector machine (LS-SVM), artificial neural networks (ANNs) and adaptive neuro-fuzzy inference system (ANFIS). The daily meteorological data for 50 years (1970–2019) were used to estimate ET0 using FAO-ET calculator. The FAO-ET calculator was compared with ML models to investigate the best-fit ML model for predicting ET. Thereafter, ET predicted by the best-fit ML model was compared with satellite (Moderate Resolution Imaging Spectroradiometer – MODIS) ET, which was finally mapped to a larger landscape (over entire Punjab and Haryana). Modeling of ET0 was best performed through LS-SVM followed by ANN2, ANN1, ANFIS10, ANFIS2, MLR and ANFIS9 models. Among developed models, coefficient of determination (R2) value varied from 0.800 to 0.998, being highest (0.998) under LS-SVM model. MODIS overestimated ET when compared with LS-SVM having R2 and root mean square error (RMSE) values of 0.73 and 3.95 mm, respectively. After applying the bias correction factor, R2 and RMSE were 0.74 and 1.19 mm, respectively. The ML and satellite-based ET estimation would be useful for timely water budgeting to manage the water scarcity problems from local to regional levels.

Application of WOA-Based LSSVM Model for Wind Speed Prediction in Mianyang, China

In recent years, countries have vigorously developed renewable energy resources to alleviate energy shortages and improve the environment. Wind energy, as a clean and renewable new energy source, has been increasing its power generation capacity, but the wind power generation itself has the characteristics of volatility and instability which makes wind power generation more difficult. Therefore, a novel prediction model based on the least squares support vector machine (LSSVM) with whale optimization algorithm (WOA) is proposed in the paper to improve the prediction accuracy and applied to the wind speed prediction in Mianyang. The model is implemented in python language, and then the prediction results are then evaluated quantitatively using the mean absolute percentage error (MAPE), and the results of the proposed model are compared with models such as eXtreme Gradient Boosting (XGBoost), Support Vector Regression (SVR) and Random Forest (RF). Further, the MAPE of the prediction results of the proposed model is about 4.7%-5.5%, which can be 6.3% higher than other models at best. The results show that the proposed prediction model can have good prediction accuracy and generalization performance and can be applied to other fields in the future.

A data-driven workflow based on multisource transfer machine learning for gas-bearing probability distribution prediction: A case study

Machine learning (ML) plays an important role in gas-bearing prediction based on multicomponent seismic data because it can reveal the complex relationship between reservoirs and their seismic attributes by establishing a nonlinear model. However, the degree of exploration in several areas remains limited, leading to insufficient sample data. Transfer learning (TL) can provide a feasible solution to this limitation by transferring learning information between data-rich sources and data-sparse target sources to accomplish a target task. Therefore, a data-driven workflow based on multisource TL is developed for predicting gas-bearing probability distribution to improve its accuracy in areas with limited sample data. First, the samples and labels of the synthetic data are established, and ML models (deep fully connected neural network and least-squares support vector machine) are applied to the synthetic data to predict the gas-bearing distribution. Subsequently, the samples and labels of the real data are established and completely mixed with the synthetic data to obtain the data set after TL. Finally, a supervised learning model is applied to predict the gas-bearing probability distribution in the study area. Adaptive mutation particle swarm optimization (AMPSO) is used to optimize the prediction performances of the two ML models. The prediction results of the AMPSO-ML are in good agreement with the actual drilling results. By comparing the prediction results after TL with those before TL, it is observed that the two models had higher efficiency and accuracy after TL, verifying the reliability of our scheme for predicting gas-bearing distribution. This method may be used for the effective prediction of gas-bearing probability distributions.

Prediction and Optimization of Blasting-Induced Ground Vibration in Open-Pit Mines Using Intelligent Algorithms

Prediction and parameter optimization are effective methods for mine personnel to control blast-induced ground vibration. However, the challenge of effective prediction and optimization lies in the multi-factor and multi-effect nature of open-pit blasting. This study proposes a hybrid intelligent model to predict ground vibrations using a least-squares support vector machine (LSSVM) optimized by a particle swarm algorithm (PSO). Meanwhile, multi-objective particle swarm optimization (MOPSO) was used to optimize the blast design parameters by considering the vibration of particular areas and the bulk rate of blast fragmentation. To compare the prediction performance of PSO-LSSVM, a genetic-algorithm-optimized BP neural network (GA-BP), unoptimized LSSVM, and BP were used, by applying the same database. In addition, the root-mean-squared error (RMSE), the mean absolute error (MAE), and the correlation coefficient (r) were regarded as the evaluation indicators. Furthermore, the optimization results of the blasting parameters were obtained by quoting the established vibration prediction model and bulk rate proxy model in MOPSO and verified by field tests. The results indicated that the PSO-LSSVM model provided the highest efficiency in predicting vibrations with an RMSE of 1.954, MAE of 1.717, and r of 0.965. Furthermore, the blasting vibration can be controlled by using the two-objective optimization model to obtain the best blasting parameters. Consequently, this study can provide more specific recommendations for vibration hazard control.

Spatial-Temporal Characteristics and Driving Forces of Aboveground Biomass in Desert Steppes of Inner Mongolia, China in the Past 20 Years

The desert steppe serves as a transitional zone between grasslands and deserts, and long-term monitoring of aboveground biomass (AGB) in the desert steppe is essential for understanding grassland changes. While AGB observation techniques based on multisource remote-sensing data and machine-learning algorithms have been widely applied, research on monitoring methods specifically for the desert steppe remains limited. In this study, we focused on the desert steppe of Inner Mongolia, China, as the study area and used field sampling data, MODIS data, MODIS-based vegetation indices (VI), and environmental factors (topography, climate, and soil) to compare the performance of four commonly used machine-learning algorithms: multiple linear regression (MLR), partial least-squares regression (PLS), random forest (RF), and support vector machine (SVM) in AGB estimation. Based on the optimal model, the spatial–temporal characteristics of AGB from 2000 to 2020 were calculated, and the driving forces of climate change and human activities on AGB changes were quantitatively analyzed using the random forest algorithm. The results are as follows: (1) RF demonstrated outstanding performance in terms of prediction accuracy and model robustness, making it suitable for AGB estimation in the desert steppe of Inner Mongolia; (2) VI contributed the most to the model, and no significant difference was found between soil-adjusted VIs and traditional VIs. Elevation, slope, precipitation, and temperature all had positive effects on the model; (3) from 2000 to 2020, the multiyear average AGB in the study area was 58.34 g/m2, exhibiting a gradually increasing distribution pattern from the inner region to the outer region (from north to south); (4) from 2000 to 2020, the proportions of grassland with AGB slightly and significantly increasing trend in the study area were 87.08% and 5.13%, respectively, while the proportions of grassland with AGB slightly and significantly decreasing trend were 7.76% and 0.05%, respectively; and (5) over the past 20 years, climate change, particularly precipitation, has been the primary driving force behind AGB changes of the study area. This research holds reference value for improving desert steppe monitoring capabilities and the rational planning of grassland resources.

Dissolved Oxygen Prediction Model for the Yangtze River Estuary Basin Using IPSO-LSSVM

Water ecology has always been key to environmental protection, and the combination of human activities and natural factors has caused eutrophication in the Yangtze estuary and adjacent waters. Among them, dissolved oxygen (DO) concentration is the key indicator to judge the quality of water. Firstly, using principal component analysis (PCA) to determine the number of parameters affecting dissolved oxygen concentration, the least squares support vector machine (LSSVM) prediction model with improved particle swarm optimization (IPSO) is proposed to be applied to the dissolved oxygen prediction in Shanghai’s Yangtze River basin through the data-driven modeling approach and the regression prediction capability of the neural network. Eight parameters of water temperature (WT), pH, potassium permanganate (KMnO4), ammonia nitrogen (NH4+-N), total phosphorus (TP), total nitrogen (TN), conductivity (Cond), and nephelometric turbidity unit (NTU) are selected as model inputs in the published public data, and the output is the dissolved oxygen concentration. The optimal combination of model parameters is found according to the IPSO algorithm, which effectively overcomes the parameter selection problem of regular support vector machines (SVM). The mean absolute error (MAE), root mean square error (RMSE), mean absolute percentage error (MAPE), and correlation coefficients of the evaluation indexes of this model (R2) are 0.1702, 0.2221, 0.0267, and 0.9751, respectively. Compared with other similar data driven models, this model has improved model accuracy and stability in predicting DO concentrations in the estuary, and thus it provides technical support for assessing and monitoring offshore water quality.

Precision Motion Control of a Piezoelectric Actuator via a Modified Preisach Hysteresis Model and Two-Degree-of-Freedom H-Infinity Robust Control.

The nonlinear hysteresis phenomenon can occur in piezoelectric-driven nanopositioning systems and can lead to reduced positioning accuracy or result in a serious deterioration of motion control. The Preisach method is widely used for hysteresis modeling; however, for the modeling of rate-dependent hysteresis, where the output displacement of the piezoelectric actuator depends on the amplitude and frequency of the input reference signal, the desired accuracy cannot be achieved with the classical Preisach method. In this paper, the Preisach model is improved using least-squares support vector machines (LSSVMs) to deal with the rate-dependent properties. The control part is then designed and consists of an inverse Preisach model to compensate for the hysteresis nonlinearity and a two-degree-of-freedom (2-DOF) H-infinity feedback controller to enhance the overall tracking performance with robustness. The main idea of the proposed 2-DOF H-infinity feedback controller is to find two optimal controllers that properly shape the closed-loop sensitivity functions by imposing some templates in terms of weighting functions in order to achieve the desired tracking performance with robustness. The achieved results with the suggested control strategy show that both hysteresis modeling accuracy and tracking performance are significantly improved with average root-mean-square error (RMSE) values of 0.0107 μm and 0.0212 μm, respectively. In addition, the suggested methodology can achieve better performance than comparative methods in terms of generalization and precision.

Multi-step wind speed prediction based on LSSVM combined with ESMD and fractional-order beetle swarm optimization

Accurate and stable wind speed prediction can alleviate the uncertain impacts of wind power generation caused by nonlinear characteristics of wind speed, and then improve the reliability of wind power. In this paper, a hybrid model for wind speed prediction based on mode decomposition, parameter optimization and basic prediction model is proposed. First, the extreme-point symmetric mode decomposition (ESMD) is employed to adaptively decompose the denoised wind speed time series into sub-sequences with different frequencies. Second, a fractional-order beetle swarm optimization (FO-BSO) for parameter optimization of the Least squares support vector machine (LSSVM) is proposed. Through benchmark functions and non-parametric statistical test, the advantages of the FO-BSO in accuracy, stability and convergence speed are verified. Subsequently, the ESMD-FO-BSO-LSSVM prediction model is established, and three groups of wind speed datasets with different sampling locations and sampling frequencies are selected for simulation experiments. The results show that the coefficient of determination of 1-step prediction of the proposed model in three datasets are 0.9856, 0.9713, 0.9940, which has 2.43%, 3.38%, 3.08% average promotion than that of 7 comparative models. And the accuracy and stability of ESMD-FO-BSO-LSSVM model in multi-step wind speed prediction have also achieved better performance than 7 competitors.