Single Support Vector Machine Research Articles

The intelligent operation and maintenance method and experimental research of CNC machine tool bearings

As the core components of high-precision rotary machine tools, machine tool bearings are prone to failure or damage, and their running state directly affects the safety and reliability of the entire equipment. Therefore, the paper proposes an intelligent operation and health management method for machine tool bearings based on Bayes-VMD-KPCA, Bayes-CNN-SVM, and health status evaluation index. Aiming at the complex working environment and high nonlinear degree of fault features of machine tool bearings, the Bayes-VMD-KPCA algorithm is used to perform variational mode decomposition of the original signal of the bearing fault, which avoids the influence of background noise and solves the problem of high dimension of multi-domain fault feature set. Second, the CNN-SVM fault diagnosis model uses a convolutional neural network (CNN) to deeply mine the extracted multi-domain fault features, and a support vector machine (SVM) can be used as a fault classifier to complete the diagnosis of various fault types of machine tool bearings. At the same time, the Bayes algorithm is introduced to tune the hyperparameters in the CNN-SVM model to further improve the prediction performance of the CNC machine tool-bearing fault diagnosis model. The results show that the intelligent operation and maintenance and health management method of CNC machine tool bearings proposed in this paper can effectively complete the fault type diagnosis and health status assessment of bearings, and its accuracy index reaches 99.33%. Compared with the single SVM model, Bayes-CNN model, Bayes-SVM model, and CNN-SVM model, the health effect is evaluated. The accuracy is increased by 6.33%, 4.33%, 2.66%, and 1%, respectively. It can be seen that the proposed method can more effectively realize the monitoring and health management of bearing fault.

Design and experiment of non-destructive testing system for moisture content of in-situ maize ear kernels based on VIS-NIR

To facilitate rapid, non-destructive, cost-effective continuous detection of Moisture Content in corn kernels, a Near-infrared (VIS-NIR) spectroscopy based in-situ maize ear moisture detection device was developed, utilizing machine learning for predictive modeling. Field experiments (30–35 °C) assessed three preprocessing algorithms: z-score normalization (ZS), Orthogonal Signal Correction (OSC), and a ZS-OSC combination, with ZS-OSC selected for its superior performance (R2 ≥ 0.90, RMSE ≤ 2.12 %, RPD＞2.9). Spectral imaging from 410 to 940 nm was used to develop moisture prediction models via Partial Least Squares Regression (PLSR) and Support Vector Machine (SVM), where PLSR is suited for single variety (R2 ≥ 0.82, RMSE ≤ 2.62 %, RPD ≥ 2.2) and SVM for both single and mixed varieties. Additionally, grain temperature's impact on model performance was analyzed, showing decreased accuracy across temperatures of 30–35 °C, 35–40 °C, and 40–45 °C. The final device and models excelled in 30–35 °C field tests, achieving R2 ≥ 0.88, RPD＞2.5, RMSE ≤ 0.901 %, with less than 1.82 % deviation between predicted and actual values, and all classification indices over 84.38 %. The device is proven accurate and effective for corn grain moisture detection, offering valuable insights for in-situ maize moisture content analysis.

A deep residual neural network model for synchronous motor fault diagnostics

Synchronous motors play a significant role in a wide range of industrial applications. Their reliable operation is paramount. Any faults in synchronous motors can lead to costly downtime, decreased productivity, and potential safety hazards. By accurately diagnosing and classifying faults, we can proactively address issues before they escalate, ensuring the smooth operation of synchronous motors and minimizing the risk of equipment failure. The accurate diagnosis and fault detection in synchronous motors pose a significant challenge in their operation and maintenance. In the existing models, the feature data at various depths are not thoroughly extracted to maximize their feature extraction capability. Additionally, they employ a single support vector machine to make the final decision on the output. The single support vector machine may not consistently produce more accurate outcomes. Therefore, this paper proposes a novel fault diagnosis model based on a deep residual neural network and multiple support vector machines to diagnose mechanical and electrical faults of synchronous motors. The proposed model improves upon existing fault diagnosis models in two key aspects. Firstly, by employing a deep neural network, the model is able to effectively process and extract fault features from the motor fault dataset, capturing more nuanced information that may be missed by existing models. Secondly, the use of multiple support vector machines enhances the decision-making capability of the model, allowing for more accurate fault diagnosis. By combining these two aspects, the proposed model achieves superior diagnostic performance compared to single support vector machine-based models. Our proposed model has been rigorously evaluated using mechanical and electrical fault datasets, and the results of experimental tests clearly demonstrate its superior diagnostic performance when compared to existing fault diagnosis models. The synergy of deep neural networks and multiple support vector machines not only improves fault detection accuracy but also enhances the robustness and generalizability of the model, making it a valuable tool for real-world industrial applications.

Assessment of Zero-Day Vulnerability using Machine Learning Approach

Organisations and people are seriously threatened by zero-day vulnerabilities because they may be utilised by attackers to infiltrate systems and steal private data. Currently, Machine Learning (ML) techniques are crucial for finding zero-day vulnerabilities since they can analyse huge datasets and find patterns that can point to a vulnerability. This research’s goal is to provide a reliable technique for detecting intruders and zero-day vulnerabilities in software systems. The suggested method employs a Deep Learning (DL) model and an auto-encoder model to find unusual data patterns. Additionally, a model for outlier detection that contrasts the autoencoder model with the single class-based Support Vector Machine (SVM) technique will be developed. The dataset of known vulnerabilities and intrusion attempts will be used to train and assess the models.

HLEL: A wetland classification algorithm with self-learning capability, taking the Sanjiang Nature Reserve I as an example

Wetland ecosystems have been severely damaged by atmospheric pollution and other environmental problems for decades. Reasonable protection, restoration, and utilization of wetlands have become priorities for environmental protection. Obtaining high-precision wetland map products is essential for ecological research as well as formulation and implementation of conservation policies. This study proposes a hierarchical labeling ensemble learning (HLEL) algorithm with self-learning capabilities to achieve high-precision wetland land cover and land use (LULC) classification by adapting self-learning hierarchical results. This study evaluated the classification performance of HLEL, random forest (RF), support vector machine (SVM), artificial neural network (ANN), and Gaussian Naive Bayes' (GNB) with GF-6 WFV multispectral images as the database and Sanjiang National Nature Reserve I in China as the study area. The results showed that the HLEL algorithm has an advantage over a single algorithm when using the feature set filtered by ReliefF, even if the complete feature set is used without feature selection. The overall accuracy of the classification results is improved by 0.4%, 5.8%, 1.3%, and 9.0% when compared to the four single algorithms RF, SVM, ANN, and GNB, respectively. In robustness tests, HLEL consistently outperformed the other algorithms for different training sample set sizes, with overall accuracy improvements of 0.4–6.9%, 5.8–11.5%, 1.3–4.4%, and 9.0–14.0% compared with RF, SVM, ANN, and GNB, respectively. The overall accuracy standard deviation of HLEL is 1.22%, proving that HLEL has low sensitivity to the size of the training data. The HLEL algorithm demonstrates exceptional precision when applied to diverse datasets. The overall accuracy of HLEL in Sentinel 2, Landsat 8, and GF-6 WFV increased by 3.1% to 22.7%, 3.1% to 39.0%, and 0.4% to 9.0%, respectively, when compared to the overallaccuracy of the basicclassifiers. The results demonstrate the feasibility of HLEL, an algorithm with high accuracy and data robustness, in applying wetland LULC classification and providing a new solution for wetland cover mapping.

A Comparative Study of Genetic Algorithm-Based Ensemble Models and Knowledge-Based Models for Wildfire Susceptibility Mapping

Wildfire susceptibility mapping (WSM) plays a crucial role in identifying areas with heightened vulnerability to forest fires, allowing for proactive measures in fire prevention, management, and resource allocation, ultimately leading to more effective fire control and mitigation strategies. This paper describes our undertaking to develop and compare the performance of two knowledge-based models, namely the analytic hierarchy process (AHP) and the technique for order performance by similarity to ideal solution (TOPSIS), as well as two novel genetic algorithm (GA)-based ensemble data-driven models: boosting and random subspace. The objective was to map susceptibility to forest fires in the Northern Mazar District in Jordan. The ensemble models were constructed using four well-known classifiers: decision tree (DT), support vector machine (SVM), k-nearest neighbors (kNN), and naive Bayes (NB) algorithms. This study utilized seventy forest fire locations and twelve influential factors to build and evaluate the models. To identify the optimal features for constructing the data-driven models, a GA-based wrapper method and four machine learning models were applied. During the validation phase, the area under the receiver operating characteristic curve (AUROCC) values for the single SVM, single NB, single DT, single kNN, GA-based boosting, GA-based random subspace, FR-AHP, and AHP-TOPSIS models were found to be 85.3%, 85.9%, 73.8%, 88.7%, 95.0%, 95.0%, 74.0%, and 65.4% respectively. The results indicated that the GA-based ensemble models outperformed both the single machine learning models and the knowledge-based techniques in terms of performance. The developed models in this study can be effectively utilized in various management and decision-making processes aimed at mitigating forest fire risks and enhancing fire control strategies.

Decision Tree Versus Linear Support Vector Machine Classifier in the Screening of Medial Speech Sounds: A Quest for a Sound Rationale.

This paper describes the latest development in the classification stage of our Speech Sound Disorder (SSD) Screening algorithm and presents the results achieved by using two classifier models: the Classification and Regression Tree (CART)-based model versus the Single Decision Hyperplane-based Linear Support Vector Machine (SVM) model. For every single speech sound in medial position, 10 features extracted from the audio samples along with an 11th feature representing the validation of the (mis)pronunciation by the Speech Language Pathologist (SLP) were fed into the 2 classifiers to compare and discuss their performance. The accuracy achieved by the two classifiers on a data test size of 30% of the analyzed samples was 98.2% for the Linear SVM classifier, and 100% for the Decision Tree classifier, which are optimal results that encourage our quest for a sound rationale.

Estimation of recompression coefficient of soil using a hybrid ANFIS-PSO machine learning model

Recompression coefficient (Cr) is =an essential parameter utilized to predict consolidation settlement of over-consolidated soil. Thus, the main aim of this work was to estimate accurately the Cr, using a hybrid ANFIS-PSO Machine Learning (ML) model that is a hybridization of Adaptive Neuro-Fuzzy Inference System (ANFIS) and Particle Swarm Optimization (PSO). To compare the performance of proposed model, we selected two other benchmark ML models: single ANFIS and Support Vector Machines (SVM). We collected and utilized the data of304 soil samples tested from various construction projects in Vietnam, which included 12 input variables (soil parameters) and one output variable (Cr). Validation indices, namely Correlation Coefficient (R), Root Mean Square Error (RMSE), and Mean Absolute Error (MAE) were utilized for the validation of the model’s performance. Correlation analysis of feature selection results indicated that seven input variables namely clay content, plasticity index, liquidity index, degree of saturation, specific gravity, dry density, and bulk density were of importance and thus selected for prediction of the Cr. Validation results indicated that predictive capability of the hybrid ANFIS-PSO model (R = 0.802) is the best in comparison with other two benchmark models namely SVM (R = 0.727) and single ANFIS (R = 0.734). The findings of our study suggest that the ANFIS-PSO is a powerful ML tool for effectively and quickly prediction of the Cr of soil. This can help save time and reduce costs associated with laboratory experiments for determining this important geotechnical parameter.

Klasifikasi Nasabah Potensial menggunakan Algoritma Ensemble Least Square Support Vector Machine dengan AdaBoost

In the era of business and economics that are interconnected with each other and competition between companies in seeking market share so that there will be an increase, especially in the number of customers, especially deposit customers, financial institutions and other companies are increasingly realizing the importance of understanding and identifying potential customers correctly to get potential customers. customers subscribe to deposits. Potential customer classification is a strategic approach that allows financial institutions to identify potential customers who have the potential to subscribe to deposits. With a deeper understanding of the characteristics and needs of potential customers, financial institutions can direct marketing resources more effectively, increase marketing efforts, and increase the conversion of potential customers to active customers. The aim of this research is to develop and test the Ensemble Least Square Support Vector Machine model with AdaBoost in classifying potential customers which can increase accuracy in identifying potential customers who have the potential to subscribe to deposits. The research results showed that this method achieved an accuracy of 95.15%, a sensitivity of 92.93%, and a specificity of 97.61%. In comparison with single Support Vector Machine and Least Squares Support Vector Machine models, the Ensemble Least Squares Support Vector Machine outperforms both in terms of accuracy.

An ensemble learning approach for resampling forgery detection using Markov process

Resampling is an extremely well-known technique performed for Image forgery detection. It includes the changes in the content of a picture in terms of rotation, stretching/zooming, and shrinking, to frame a forged picture that is a localized forgery in comparison to the original picture. With the wrong intention, resampling forgery has been increased day by day, and its negative impact has been increased in criminology, law enforcement, forensics, research etc. Accordingly, the interest in the algorithm of image resampling forgery detection is significantly developed in image forensics. In this paper, a novel image resampling forgery detection technique has been proposed. In the proposed technique, two types of Markov feature with spatial and Discrete Cosine Transform domains have been extracted to recognize the resampling operation. The spatial domain gives the information for the distribution of the pixels and DCT gives the edge information. Further, these Markov features are consolidated. Due to high dimensionality hard thresholding technique is used for reducing the dimensionality. Then, these Markov features are applied to the set of models of different classifiers. With the utilization of classifiers, weighted majority voting values have been calculated during the ensemble classification. Unlike the other techniques, these weighted voting boundaries have been consequently balanced during the training process until the best accuracy has been obtained. However, it is very difficult to get best accuracy so for getting best accuracy this research needs to do lots of iterations and trained the dataset. For the comparative study very few research has been found for this resampling forgery technique with different interpolation techniques and classifier. Still, comparison has been done with some latest research work. The comparative analysis shows that the proposed ensemble learning-based algorithm provides the best outcomes with the accuracy of 99.12% for bicubic, 98.89% for bilinear, and 98.23% for lanczos3 kernel with considerably less complexity and high speed in comparison to prior techniques which are using single support vector machine for classification. Moreover, the proposed algorithm also detects a very low probability of error of 0.44% and detects the type of interpolation kernel, size of the forgery, and the type of resampling, whether it is up sampling and down sampling, using Graphical User Interface which has not been detected previously with multiple forgery detection.

The Detection of Kiwifruit Sunscald Using Spectral Reflectance Data Combined with Machine Learning and CNNs

Sunscald in kiwifruit, an environmental stress caused by solar radiation during the summer, reduces fruit quality and yields and causes economic losses. The efficient and timely detection of sunscald and similar diseases is a challenging task but helps to implement measures to control stress. This study provides high-precision detection models and relevant spectral information on kiwifruit physiology for similar statuses, including early-stage sunscald, late-stage sunscald, anthracnose, and healthy. Primarily, in the laboratory, 429 groups of spectral reflectance data for leaves of four statuses were collected and analyzed using a hyperspectral reflection acquisition system. Then, multiple modeling approaches, including combined preprocessing methods, feature extraction algorithms, and classification algorithms, were designed to extract bands and evaluate the performance of the models to detect the statuses of kiwifruit. Finally, the detection of different stages of kiwifruit sunscald under anthracnose interference was accomplished. As influential bands, 694–713 nm, 758–777 nm, 780–799 nm, and 1303–1322 nm were extracted. The overall accuracy, precision, recall, and F1-score values of the models reached 100%, demonstrating an ability to detect all statuses with 100% accuracy. It was concluded that the combined processing of moving average and standard normal variable transformations (MS) could significantly improve the data; the near-infrared support vector machine and visible convolutional neural network with MS (NIR-MS-SVM and VIS-MS-CNN) were established as high-precision detection techniques for the classification of similar kiwifruit statuses, demonstrating 25.58% higher accuracy than the single support vector machine. The VIS-MS-CNN model reached convergence with a stable cross-entropy loss of 0.75 in training and 0.77 in validation. The techniques developed in this study will improve orchard management efficiency and yields and increase researchers’ understanding of kiwifruit physiology.

Robust Key Update With Controllable Accuracy Using Support Vector Machine for Secure OFDMA-PON

In this paper, we first propose a novel secret key update scheme only with a single support vector machine (SVM). To achieve robust and efficient key management for secure orthogonal frequency division multiple access-based passive optical network (OFDMA-PON). The key sequences required to be shared between multiple optical network units (ONUs) and optical line terminal (OLT) are converted into partial quadrature amplitude modulation (QAM) symbol phases, and then masked into the whole upstream signal using two-dimensional chaos. The session keys can be distributed in real-time without consuming exclusive secure channels and resulting in data rate loss. A well-trained support vector machine (SVM) implemented at the receiver enables error-free key decision. Moreover, the numerous cross validations are conducted to verify the superior generalization performance under various parameters including key length and modulation format. The 16-QAM, 32-QAM, and 64-QAM OFDM signal transmissions are successfully demonstrated over 25 km standard single mode fiber (SSMF) by an experiment. The results show that the controllable restored accuracy of key can be realized by regulating the pivotal algorithm parameter to flexibly adapt to different system conditions, thus this scheme can be a promising efficient key update technology for future secure PON.

Bayes' Theorem for Multi-Bearing Faults Diagnosis

During the process of fault diagnosis for automated machinery, support vector machines is one of the suitable choices to categorize multiple faults for machinery. Regardless of the volume of sampling data, support vector machines can handle a high number of input features. It was learned that support vector machines could only sense binary fault classification (such as faulty or healthy). However, the classification accuracy was found to be lower when using support vector machines to diagnose multi-bearing faults classifications. This is because the multiple classification problem will be reduced into several sub-problems of binary classification when support vector machines adapt to multi-bearing faults classifications. From there, many contradictory results will occur from every support vector machine model. In order to solve the situation, the combination of Support Vector Machines and Bayes’ Theorem is introduced to every single support vector machine model to overcome the conflicting results. This method will also increase classification accuracy. The proposed Support Vector Machines - Bayes’ Theorem method has resulted in an increase in the accuracy of the fault diagnosis model. The analysis result has shown an accuracy from 72% to 95%. It proved that Support Vector Machines - Bayes’ Theorem continuously eliminates and refines conflicting results from the original support vector machine model. Compared to the existing support vector machine, the proposed Support Vector Machines - Bayes’ Theorem has proven its effectiveness in diagnosing the multi-bearing faults problem classification.

Research on Fault Diagnosis of HVAC Systems Based on the ReliefF-RFECV-SVM Combined Model

A fault diagnosis method of heating, ventilation, and air conditioning (HVAC) systems based on the ReliefF-recursive feature elimination based on cross validation-support vector machine (ReliefF-RFECV-SVM) combined model is proposed to enhance the diagnosis accuracy and efficiency. The method initially uses ReliefF to screen the original features, selecting those that account for 95% of the total weight. The recursive feature elimination based on cross validation (RFECV), based on a random forest classifier, is then applied to select the optimal feature subset according to diagnostic accuracy. Finally, a support vector machine (SVM) model is constructed for fault classification. The method is tested on seven typical faults of the ASHRAE 1043-RP water chiller dataset and three typical faults of an air-cooled self-built air conditioner simulation dataset. The results show that the ReliefF-RFECV-SVM method significantly reduces diagnosis time compared to SVM, shortening it by about 50% based on the ASHRAE 1043-RP dataset, while achieving an overall accuracy of 99.98%. Moreover, the proposed method achieves a comprehensive diagnosis accuracy of 99.97% on the self-built simulation dataset, with diagnosis time the reduced by about 65% compared to single SVM.

A Support Vector Machine-Based Approach for Bolt Loosening Monitoring in Industrial Customized Vehicles.

Machine learning techniques have progressively emerged as important and reliable tools that, when combined with machine condition monitoring, can diagnose faults with even superior performance than other condition-based monitoring approaches. Furthermore, statistical or model-based approaches are often not applicable in industrial environments with a high degree of customization of equipment and machines. Structures such as bolted joints are a key part of the industry; therefore, monitoring their health is critical to maintaining structural integrity. Despite this, there has been little research on the detection of bolt loosening in rotating joints. In this study, vibration-based detection of bolt loosening in a rotating joint of a custom sewer cleaning vehicle transmission was performed using support vector machines (SVM). Different failures were analyzed for various vehicle operating conditions. Several classifiers were trained to evaluate the influence of the number and location of accelerometers used and to determine the best approach between specific models for each operating condition or a single model for all cases. The results showed that using a single SVM model with data from four accelerometers mounted both upstream and downstream of the bolted joint resulted in more reliable fault detection, with an overall accuracy of 92.4%.

Support Vector Machine Chains with a Novel Tournament Voting

Support vector machine (SVM) algorithms have been widely used for classification in many different areas. However, the use of a single SVM classifier is limited by the advantages and disadvantages of the algorithm. This paper proposes a novel method, called support vector machine chains (SVMC), which involves chaining together multiple SVM classifiers in a special structure, such that each learner is constructed by decrementing one feature at each stage. This paper also proposes a new voting mechanism, called tournament voting, in which the outputs of classifiers compete in groups, the common result in each group gradually moves to the next round, and, at the last round, the winning class label is assigned as the final prediction. Experiments were conducted on 14 real-world benchmark datasets. The experimental results showed that SVMC (88.11%) achieved higher accuracy than SVM (86.71%) on average thanks to the feature selection, sampling, and chain structure combined with multiple models. Furthermore, the proposed tournament voting demonstrated higher performance than the standard majority voting in terms of accuracy. The results also showed that the proposed SVMC method outperformed the state-of-the-art methods with a 6.88% improvement in average accuracy.

Multi-Modal Late Fusion Rice Seed Variety Classification Based on an Improved Voting Method

Rice seed variety purity, an important index for measuring rice seed quality, has a great impact on the germination rate, yield, and quality of the final agricultural products. To classify rice varieties more efficiently and accurately, this study proposes a multimodal l fusion detection method based on an improved voting method. The experiment collected eight common rice seed types. Raytrix light field cameras were used to collect 2D images and 3D point cloud datasets, with a total of 3194 samples. The training and test sets were divided according to an 8:2 ratio. The experiment improved the traditional voting method. First, multiple models were used to predict the rice seed varieties. Then, the predicted probabilities were used as the late fusion input data. Next, a comprehensive score vector was calculated based on the performance of different models. In late fusion, the predicted probabilities from 2D and 3D were jointly weighted to obtain the final predicted probability. Finally, the predicted value with the highest probability was selected as the final value. In the experimental results, after late fusion of the predicted probabilities, the average accuracy rate reached 97.4%. Compared with the single support vector machine (SVM), k-nearest neighbors (kNN), convolutional neural network (CNN), MobileNet, and PointNet, the accuracy rates increased by 4.9%, 8.3%, 18.1%, 8.3%, and 9%, respectively. Among the eight varieties, the recognition accuracy of two rice varieties, Hannuo35 and Yuanhan35, by applying the voting method improved most significantly, from 73.9% and 77.7% in two dimensions to 92.4% and 96.3%, respectively. Thus, the improved voting method can combine the advantages of different data modalities and significantly improve the final prediction results.

Slope stability prediction based on adaptive CE factor quantum behaved particle swarm optimization-least-square support vector machine

Since the prediction of slope stability is affected by the combination of geological and engineering factors with uncertainties such as randomness, vagueness and variability, the traditional qualitative and quantitative analysis cannot match the recent requirements to judge them accurately. In this study, we expect that the adaptive CE factor quantum behaved particle swarm optimization (ACE-QPSO) and least-square support vector machine (LSSVM) can improve the prediction accuracy of slope stability. To ensure the global search capability of the algorithm, we introduced three classical benchmark functions to test the performance of ACE-QPSO, quantum behaved particle swarm optimization (QPSO), and the adaptive dynamic inertia weight particle swarm optimization (IPSO). The results show that the ACE-QPSO algorithm has a better global search capability. In order to evaluate the stability of the slope, we followed the actual project and research literature and selected the unit weight, slope angle, height, internal cohesion, internal friction angle and pore water pressure as the main indicators. To determine whether the algorithm is scientifically and practically feasible for slope deformation prediction, the ACE-QPSO-, QPSO-, IPSO-LSSVM and single least-square support vector machine algorithms were trained and tested based on a real case of slope project with six index factors as the input layer of the LSSVM model and the safety factor as the output layer of the model. The results show that the ACE-QPSO-LSSVM algorithm has a better model fit (R2=0.8030), minor prediction error (mean absolute error=0.0825, mean square error=0.0110) and faster convergence (second iteration), which support that the ACE-QPSO-LSSVM algorithm emthod is more feasible and efficient in predicting slope stability.

Prediction of Main Parameters of Steam in Waste Incinerators Based on BAS-SVM

The main steam parameters of a waste-to-energy plant are the key indicator of the safety and stability of its combustion process. Accurate prediction of the main steam parameters can help the control system to reasonably analyze the combustion conditions and, thus, to greatly improve the combustion efficiency. In this paper, we propose an optimized method for predicting the main steam parameters of waste incinerators. Firstly, a grey relational analysis (GRA) is used to obtain the ranking of the correlation degree between 114 characteristic variables in the furnace and the main steam parameters, and 13 characteristic variables are selected as model inputs. A Spearman-based time delay compensation method is proposed to effectively overcome the influence of time asynchrony on the prediction accuracy. At last, the beetle antennae search (BAS) optimized support vector machine (SVM) model is proposed. Taking advantage of the fast iteration of the beetle antennae search algorithm to find the key hyperparameters of the support vector machine, the optimized main steam parameter prediction model is finally obtained. The simulation results show that the prediction accuracy of this model is greatly improved compared with traditional neural network models, such as long short-term memory neural networks (LSTMs) and convolutional neural networks (CNNs), as well as a single SVM.

Fast Sleep Stage Classification Using Cascaded Support Vector Machines with Single-Channel EEG Signals.

Long-term sleep stage monitoring is very important for the diagnosis and treatment of insomnia. With the development of wearable electroencephalogram (EEG) devices, we developed a fast and accurate sleep stage classification method in this study with single-channel EEG signals for practical applications. The original sleep recordings were collected from the Sleep-EDF database. The wavelet threshold denoising (WTD) method and wavelet packet transformation (WPT) method were applied as signal preprocessing to extract six kinds of characteristic waves. With a comprehensive feature system including time, frequency, and nonlinear dynamics, we obtained the sleep stage classification results with different Support Vector Machine (SVM) models. We proposed a novel classification method based on cascaded SVM models with various features extracted from denoised EEG signals. To enhance the accuracy and generalization performance of this method, nonlinear dynamics features were taken into consideration. With nonlinear dynamics features included, the average classification accuracy was up to 88.11% using this method. In addition, with cascaded SVM models, the classification accuracy of the non-rapid eye movement sleep stage 1 (N1) was enhanced from 41.5% to 55.65% compared with the single SVM model, and the overall classification time for each epoch was less than 1.7 s. Moreover, we demonstrated that it was possible to apply this method for long-term sleep stage monitor applications.