Traditional Support Vector Machine Model Research Articles

Accurate categorization and rapid pathological diagnosis correction with Micro-Raman technique in human lung adenocarcinoma infiltration level.

In the context of surgical interventions for lung adenocarcinoma (LADC), precise determination of the extent of LADC infiltration plays a pivotal role in shaping the surgeon's strategic approach to the procedure. The prevailing diagnostic standard involves the expeditious intraoperative pathological diagnosis of areas infiltrated by LADC. Nevertheless, current methodologies rely on the visual interpretation of tissue images by proficient pathologists, introducing an error margin of up to 15.6%. In this study, we investigated the utilization of Micro-Raman technique on isolated specimens of human LADC with the objective of formulating and validating a workflow for the pathological diagnosis of LADC featuring diverse degrees of infiltration. Our strategy encompasses a thorough pathological characterization of LADC, spanning different tissue types and levels of infiltration. Through the integration of Raman spectroscopy with advanced deep learning models for simultaneous diagnosis, this approach offers a swift, precise, and clinically relevant means of analysis. The diagnostic performance of the convolutional neural network (CNN) model, coupled with the microscopic Raman technique, was found to be exceptional and consistent, surpassing the traditional support vector machine (SVM) model. The CNN model exhibited an area under the curve (AUC) value of 96.1% for effectively distinguishing normal tissue from LADC and an impressive 99.0% for discerning varying degrees of infiltration in LADCs. To comprehensively assess its clinical utility, Raman datasets from patients with intraoperative rapid pathologic diagnostic errors were utilized as test subjects and input into the established CNN model. The results underscored the substantial corrective capacity of the Micro-Raman technique, revealing a misdiagnosis correction rate exceeding 96% in all cases. Ultimately, our discoveries highlight the Micro-Raman technique's potential to augment the intraoperative diagnostic precision of LADC with varying levels of infiltration. And compared to the traditional SVM model, the CNN model has better generalization ability in diagnosing different infiltration levels. This method furnishes surgeons with an objective groundwork for making well-informed decisions concerning subsequent surgical plans.

Forecast earthquake precursor in the Flores Sea

<span>Artificial intelligence (AI) can use seismic training data to discover relationships between inputs and outcomes in real-world applications. Despite this, particularly when using geographical data, it has not been used to predict earthquakes in the Flores Sea. The algorithm will read the seismic data as a pattern of iterations throughout the operation. The output data is created by grouping based on clusters using the most effective WCSS analysis, while the input features are derived from the original international resource information system (IRIS) web service data. Given that earthquake prediction is an effort to reduce seismic disasters, this research is essential. By generating predictions, it can reduce the devastation caused by earthquakes. Using the support vector machine (SVM), hyperparameter support vector machine (HP-SVM), and particle swarm optimization support vector machine (PSO-SVM) algorithms, this study seeks to forecast the Flores Sea earthquake. According to the estimation results, the SVM algorithm’s evaluation value is less precise than that of the HP-SVM, especially the linear HP-SVM and HP-SVM Polynomial models. However, the HP-SVM RBF model’s accuracy rating is identical to that of the traditional SVM model. <br /> The improvement of the PSO-SVM model, which has the finest gamma position and a value of 9.</span>

Deep learning-assisted diagnosis of benign and malignant parotid tumors based on contrast-enhanced CT: a multicenter study.

To develop deep learning-assisted diagnosis models based on CT images to facilitate radiologists in differentiating benign and malignant parotid tumors. Data from 573 patients with histopathologically confirmed parotid tumors from center 1 (training set: n = 269; internal-testing set: n = 116) and center 2 (external-testing set: n = 188) were retrospectively collected. Six deep learning models (MobileNet V3, ShuffleNet V2, Inception V3, DenseNet 121, ResNet 50, and VGG 19) based on arterial-phase CT images, and a baseline support vector machine (SVM) model integrating clinical-radiological features with handcrafted radiomics signatures were constructed. The performance of senior and junior radiologists with and without optimal model assistance was compared. The net reclassification index (NRI) and integrated discrimination improvement (IDI) were calculated to evaluate the clinical benefit of using the optimal model. MobileNet V3 had the best predictive performance, with sensitivity increasesof 0.111 and 0.207 (p < 0.05) in the internal- and external-testing sets, respectively, relative to the SVM model. Clinical benefit and overall efficiency of junior radiologist were significantly improved with model assistance; for the internal- and external-testing sets, respectively, the AUCs improved by 0.128 and 0.102 (p < 0.05), the sensitivity improved by 0.194 and 0.120 (p < 0.05), the NRIs were 0.257 and 0.205 (p < 0.001), and the IDIs were 0.316 and 0.252 (p < 0.001). The developed deep learning models can assist radiologists in achieving higher diagnostic performance and hopefully provide more valuable information for clinical decision-making in patients with parotid tumors. • The developed deep learning models outperformed the traditional SVM model in predicting benign and malignant parotid tumors. • Junior radiologist can obtain greater clinical benefits with assistance from the optimal deep learning model. • The clinical decision-making process can be accelerated in patients with parotid tumors using the established deep learning model.

An improved model for building energy consumption prediction based on time-series analysis

The development and popularisation of renewable energy is necessary. The application of renewable energy technology in buildings is an important research direction. Moreover, the prediction of renewable energy consumption in this direction is an essential research content. In view of this, a building energy consumption prediction model of renewable energy based on time-series analysis and a support vector machine (SVM) is proposed. The performance test of this model showed that its loss value was as low as 1.5% in the training set, and the loss value was 4.1% in the test set. In addition, it showed the highest accuracy rate of 95.5% in the neural network accuracy test, which is significantly higher than that of traditional algorithms. About the overall energy consumption prediction ability of the model, the experimental results showed that the lowest error of the energy consumption prediction model was 2.3%, the average relative error of the traditional SVM model in the same data set was 6.8% and that of the chaotic time-series model was 4.1%. Compared with the prediction ability of the traditional models currently used, the prediction ability of the energy consumption prediction model has been greatly improved, and it has the potential to be put into practical application.

Improved Support Vector Machine Personal Credit Rating Model

Credit consumption has become the choice of more and more people. While the expansion of credit consumption brings convenience, the consequent problem of discredit brings incalculable loss to trust institutions, such as intentional arrears, malicious overdraft consumption, etc. to the trust in the operation of the huge losses caused. On the one hand, our country is unable to establish perfect personal credit record, customer credit information is difficult to share, access to relevant data is limited, personal credit system is not perfect, therefore, it is necessary to establish a perfect and automatic personal credit evaluation system, identify the personal credit risk scientifically, and realize the maximization of bank credit income. In the bank risk management, the main problem is how to measure and avoid the bank's financial risk, and personal credit assessment is the most difficult and important part. In this paper, we use the XGBOOST algorithm to sort the importance of features, and select the number of features and the specific features according to the relationship between the model accuracy and the number of features, then 80% of the data was taken into the traditional Support vector machine model as a training set and tested with the remaining data with low accuracy, so that, in terms of individual credit risk assessment, this paper introduces the quadric surface into the traditional Support vector machine and builds the kernel-free quadric surface Support vector machine model, which improves the accuracy by 9.8 percentage points and has a guiding significance for the bank reference risk control.

New Results on Classification Modeling of Noisy Tensor Datasets: A Fuzzy Support Tensor Machine Dual Model

In this article, classification problems for a class of tensor datasets with a noisy environment are investigated. To address such issues, a novel fuzzy support tensor machine (FSTM) dual model with robustness is established. First, for each input sample in the noisy tensor dataset, we define three kinds of fuzzy membership functions, such as linear, cosine, and exponential forms. In particular, the reconstruction process from one-dimensional (1-D) vector data to third-order tensor data is also derived in the Appendix. Second, the original optimization model of an FSTM on fuzzy membership is designed by constructing the vector pattern of the traditional support vector machine (SVM) models into a tensor pattern. Next, by introducing the Lagrangian multiplier method and tensor-Tucker decomposition method to the original FSTM model, an FSTM dual model without tensor inner product operation is obtained for the first time. Such a dual model with tensor-Tucker decomposition form can avoid conservativeness caused by the vectorization of tensor data in the traditional SVM model. Furthermore, an FSTM classifier is derived by the designed numerical algorithm, and the classification generalization error bound of the FSTM model with a general form is developed. It is worth noting that a linear least-squares FSTM (LLS-FSTM) equation with tensor-Tucker decomposition is also designed in the Appendix to further reduce the slightly time-consuming problem of the solving the dual optimization model FSTM. Finally, two numerical examples are presented to verify the feasibility and validity of the derived FSTM classifier.

Research on Risk Features and Prediction of China’s Crude Oil Futures Market Based on Machine Learning

Facing the rapidly changing domestic and foreign futures markets, how to accurately and immediately predict the price trend of crude oil futures in order to avoid the risks caused by price fluctuations is very important for all participants in the crude oil futures market. Based on the 5-min high-frequency trading data of China’s crude oil futures market in recent 3 years, this paper uses the EMD-MFDFA model combined with multifractal detrended fluctuation analysis (MF-DFA) and empirical mode decomposition unsupervised K-means clustering and Gaussian mixture model (GMM) to identify the risk status of each trading day. Further, Support vector machine (SVM), extreme gradient lifting (XGBoost) and their improved algorithms are used to predict the risk state of China’s crude oil futures market. The empirical results are as follows: first, There are obvious multifractal features in the return rate series of China’s crude oil futures market and its single trading day; Second, compared with the traditional SVM model, the improved Twin Support Vector Machine (TWSVM) based on solving the sample imbalance issue has better prediction ability for China’s crude oil futures risk.; Third, The XGBoost has a great impact on the prediction of China’s crude oil risk, and the Focal-XGBoost with focal loss function performs the best in predicting the risk of China’s crude oil futures market.

Identifying molecular functional groups of organic compounds by deep learning of NMR data.

We preprocess the raw nuclear magnetic resonance (NMR) spectrum and extract key features by using two different methodologies, called equidistant sampling and peak sampling for subsequent substructure pattern recognition. We also provide a strategy to address the imbalance issue frequently encountered in statistical modeling of NMR data set and establish two conventional support vector machine (SVM) and K-nearest neighbor (KNN) models to assess the capability of two feature selections, respectively. Our results in this study show that the models using the selected features of peak sampling outperform those using equidistant sampling. Then we build the recurrent neural network (RNN) model trained by data collected from peak sampling. Furthermore, we illustrate the easier optimization of hyperparameters and the better generalization ability of the RNN deep learning model by detailed comparison with traditional machine learning SVM and KNN models.

Hyperspectral Image Classification Based on Non-Parallel Support Vector Machine

Support vector machine (SVM) has a good effect in the supervised classification of hyperspectral images. In view of the shortcomings of the existing parallel structure SVM, this article proposes a non-parallel SVM model. Based on the traditional parallel boundary structure vector machine, this model adds an additional empirical risk minimization term to the original optimization problem by adding the least square term of the sample and obtains two non-parallel hyperplanes, respectively, forming a new non-parallel SVM algorithm to minimize the additional empirical risk of non-parallel SVM (Additional Empirical Risk Minimization Non-parallel Support Vector Machine, AERM-NPSVM). On the basis of AERM-NPSVM, the bias constraint is added to it, and AERM-NPSVM (BC-AERM-NPSVM) is further obtained. The experimental results show that, compared with the traditional parallel SVM model and the classical non-parallel SVM model, Twin Support Vector Machine (TWSVM), the new model, has a better effect in hyperspectral image classification and better generalization performance.

Identification of Gut Flora Based on Robust Support Vector Machine

Gut flora parasitize the human gastrointestinal tract to maintain normal physiological functions, but can also lead to a variety of diseases and affect mental health. The relationship between gut flora and human health has attracted increasing attention and become a popular research hotspot at present. However, biological data are often characterized by large size and high dimensionality, leading to limited ability of traditional statistical-based methods to handle these data and make them difficult to analyze. In this paper, we use a support vector machine (SVM) model to perform data mining analysis on the Gut flora dataset. Specifically, we build a robust SVM model to compare the gut flora of obese and healthy people based on the public database of the American Gut Project, analyze the characteristics of the gut flora of obese people, and set up a machine learning model to predict the obesity status of people based on the gut flora to provide a theoretical basis for obesity intervention based on the gut flora. Different from the traditional support vector machine model, we use ramp loss to calculate the sample loss, avoid the influence of noise data, and get more accurate experimental results. The experimental results reveal the characteristics of the gut flora of obese people, apply machine learning to obesity prediction, and provide new research ideas and theoretical basis for precision diet and precision medicine.

A Novel Stacked Generalization Ensemble-Based Hybrid PSVM-PMLP-MLR Model for Energy Consumption Prediction of Copper Foil Electrolytic Preparation

At present, the energy consuming during the electrolytic copper foil preparation accounts for more than 75% of the total energy consumption. In real-life production, the process parameters are set by the operator empirically and the system may not work at the operating point with minimum energy consumption. Therefore, it is critical to establish an effective model for predicting electrolysis energy consumption to guide the parameters design. In this paper, a novel hybrid model (named PSVM-PMLP-MLR) based on stacked ensemble learning is proposed. The model is divided into two parts: the base-learning model and the meta-learning model. The support vector machine (SVM) model and multilayer perceptron (MLP) model with different input structures are established by the former first. Then the particle swarm algorithm is employed to determine the optimal value of SVM parameters and the optimal weight of MLP by minimizing the mean absolute percentage error (MAPE). The multiple linear regression (MLR) is finally employed as a meta-learning machine to compute the final predictions. Experimental results show that the regression coefficient of this model reached 0.987, and compared with the traditional SVM and MLP models, the accuracy of the model is improved by 10.29% and 8.28%, respectively.

An implicit opinion analysis model based on feature-based implicit opinion patterns

With the rapid growth of social networks, mining customer opinions based on online reviews is crucial to understand consumer needs. Due to the richness of language expressions, customer opinions are often expressed implicitly. However, previous studies usually focus on mining explicit opinions to understand consumer needs. In this paper, we propose a novel implicit opinion analysis model to perform implicit opinion analysis of Chinese customer reviews at both the feature and review levels. First, we extract an implicit-opinionated review/clause dataset from raw review dataset and introduce the concept of the feature-based implicit opinion pattern (FBIOP). Secondly, we develop a clustering algorithm to construct product feature categories. Based on the constructed feature categories, FBIOPs can be mined from the extracted implicit-opinionated clause dataset. Thirdly, the sentiment intensity and polarity of each FBIOP are calculated by using the Chi squared test and pointwise mutual information. Fourthly, according to the resulting FBIOP polarities, the polarities of implicit opinions can be determined at both the feature and review levels. Car forum reviews written in Chinese are collected and labeled as the experimental dataset. The results show that the proposed model outperforms the traditional support vector machine model and the cutting-edge convolutional neural network model.

Combining the Fisher Feature Extraction and Support Vector Machine Methods to Identify the Water Inrush Source: A Case Study of the Wuhai Mining Area

Discriminating the source of water inrush accurately and efficiently is necessary for water control in the coal mining industry. We combined the Fisher feature extraction and support vector machine (SVM) methods and applied this new model to the Wuhai mining area. The method extracts features from the raw data and integrated SVM, and synthetically considers the influence of geographical factors. Cross-analysis was tested 100 times, which arbitrarily selected 12 samples for the prediction and discrimination process. The results indicate that this new combined model of linear dimension reduction and non-linear dimension elevation was more accurate and efficient in discriminating water inrush sources than the traditional SVM model. Moreover, by reducing the penalty term of SVM model, we analyzed the correlation among the aquifers. We concluded that aquifers II and IV correlated strongly with each other, and that aquifer III was poorly connected with the other aquifers.

A 1-norm regularized linear programming nonparallel hyperplane support vector machine for binary classification problems

This research proposes a 1-norm regularized linear programming nonparallel hyperplane support vector machine (LNSVM) model to solve binary classification problems and enhance the robustness performance. Numerous nonparallel support vector machine (SVM) models have been studied with outstanding performance on classification tasks. However, most nonparallel SVM models require two independent models to determine hyperplanes. In addition, due to the involvement of the 2-norm terms, traditional SVM models may suffer from the lack of robustness to outliers and irrelevant features. Therefore, the LNSVM model is proposed by reformulating a typical nonparallel SVM model through the 1-norm regularization. By applying the exterior penalty theory, the proposed LNSVM model is converted to the dual exterior penalty problem, which is solved by the Newton–Armijo algorithm. The essential differences that distinguish the LNSVM model from other nonparallel SVM models are: (1) Different from typical nonparallel SVM models, which solve two quadratic programming (QP) problems, the proposed LNSVM model determines two nonparallel hyperplanes simultaneously by solving a single linear programming (LP) model; (2) The robustness performance of the proposed LNSVM model has been enhanced to tolerate noisy data through the involvement of 1-norm loss function, which can also eliminate redundant features by generating sparse solution during the training procedure. The performance of the proposed LNSVM model is tested through a comparison with state-of-art SVM-based classifiers using a synthetic dataset and 11 practical benchmark datasets. The experimental results show the superiority of the proposed LNSVM model, by achieving better classification performance regarding accuracy, sensitivity, specificity, and removing redundant features synchronously.

IOWA-SVM: A Density-Based Weighting Strategy for SVM Classification via OWA Operators

A weighting strategy for handling outliers in binary classification using support vector machine (SVM) is proposed in this article. The traditional SVM model is modified by introducing an induced ordered weighted averaging (IOWA) operator, in which the hinge loss function becomes an ordered weighted sum of the SVM slack variables. These weights are defined using IOWA quantifiers, while the order is induced via fuzzy density-based methods for outlier detection. The proposal is developed for both linear and kernel-based classification using the duality theory and the kernel trick. Our experimental results on well known benchmark datasets demonstrate the virtues of the proposed IOWA-SVM, which achieved the best average performance compared to other machine learning approaches of similar complexity.

Application of a new hybrid particle swarm optimization-mixed kernels function-based support vector machine model for reservoir porosity prediction: A case study in Jacksonburg-Stringtown oil field, West Virginia, USA

Porosity is a fundamental property that characterizes the storage capability of fluid and gas-bearing formations in a reservoir. An accurate porosity value can be measured from core samples in the laboratory; however, core analysis is expensive and time consuming. Well-log data can be used to calculate porosity, but the availability of log suites is often limited in mature fields. Therefore, robust porosity prediction requires integration of core-measured porosity with available well-log suites to control for changes in lithology and fluid content. A support vector machine (SVM) model with mixed kernel function (MKF) is used to construct the relationship between limited conventional well-log suites and sparse core data. Porosity is the desired output, and two conventional well-log responses (gamma ray [GR] and bulk density) and three well-log-derived parameters (the slope of GR, the slope of density, and [Formula: see text]) are input parameters. A global stochastic searching algorithm, particle swarm optimization (PSO), is applied to improve the efficiency of locating the appropriate values of five control parameters in MKF-SVM model. The results of SVM with different traditional kernel functions were compared, and the MKF-SVM model provided an improvement over the traditional SVM model. To confirm the advantage of the hybrid PSO-MKF-SVM model, the results from three models: (1) radial basis function (RBF)-based least-squares SVM, (2) multilayer perceptron artificial neural network (ANN), and (3) RBF ANN, are compared with the result of the hybrid PSO-MKF-SVM model. The results indicate that the hybrid PSO-MKF-SVM model improves porosity prediction with the highest correlation coefficient ([Formula: see text] of 0.9560), the highest coefficient of determination ([Formula: see text] of 0.9140), the lowest root-mean-square error (1.6505), average absolute error value (1.4050), and maximum absolute error (2.717).

Daily soil temperatures predictions for various climates in United States using data-driven model

As an important indicator of soil characteristics, soil temperature has a great impact on agricultural production, building energy savings and for shallow geothermal applications. Data-driven models have been developed and achieved good accuracy in monthly soil temperatures or daily soil temperatures predictions of a single site taking air temperature, solar radiant and time as inputs. Models’ accuracy obviously dropped if they are applied for predicting daily soil temperatures for various climates on a continental scale. We proposed a new data-driven model based on the support vector machine (SVM). The new model considers daily soil temperature variations as superposition of annual average ground temperatures predictions (long-term climates impact) and daily ground temperature amplitude predictions (short-term climates impact). Annual average soil temperature are determined by air temperature, solar radiant, wind speed and relative humidity; daily soil temperature amplitudes by air temperature amplitudes, solar radiant and day of year. For daily soil temperature predictions at 16 sites located in arid or dry summer climates, warm climates and snow climates in United States, the new model’s mean absolute error is 1.26 °C and root mean square error is 1.66 °C. Meanwhile, traditional SVM model’s mean absolute error is 2.20 °C and root mean square error is 2.91 °C.

Short-term nodal load forecasting method considering redundant information

The most existing short-term nodal load forecasting methods only focused on the application of separate historical data, ignoring the abundant redundant information in power system. In this paper a new nodal load forecasting method considered physical redundancy and measurement redundancy was proposed. Firstly, the effect of redundant information on short-term nodal load forecasting was analysed and the forecasting principle was given. Secondly, in order to form additional state variable measurement equations, two kinds of existing redundant information between state variable and measured values were analysed deeply. Then based on the forecasting principle and the analysis results, the forecasting model mainly imitated the form of state estimation was established and the specific forecasting process was given. Case studies demonstrated that compared with traditional support vector machine model, the proposed method could effectively decrease forecasting errors and improve forecasting results.

Estimating Forest Carbon Fluxes Using Machine Learning Techniques Based on Eddy Covariance Measurements

Approximating the complex nonlinear relationships that dominate the exchange of carbon dioxide fluxes between the biosphere and atmosphere is fundamentally important for addressing the issue of climate change. The progress of machine learning techniques has offered a number of useful tools for the scientific community aiming to gain new insights into the temporal and spatial variation of different carbon fluxes in terrestrial ecosystems. In this study, adaptive neuro-fuzzy inference system (ANFIS) and generalized regression neural network (GRNN) models were developed to predict the daily carbon fluxes in three boreal forest ecosystems based on eddy covariance (EC) measurements. Moreover, a comparison was made between the modeled values derived from these models and those of traditional artificial neural network (ANN) and support vector machine (SVM) models. These models were also compared with multiple linear regression (MLR). Several statistical indicators, including coefficient of determination (R2), Nash-Sutcliffe efficiency (NSE), bias error (Bias) and root mean square error (RMSE) were utilized to evaluate the performance of the applied models. The results showed that the developed machine learning models were able to account for the most variance in the carbon fluxes at both daily and hourly time scales in the three stands and they consistently and substantially outperformed the MLR model for both daily and hourly carbon flux estimates. It was demonstrated that the ANFIS and ANN models provided similar estimates in the testing period with an approximate value of R2 = 0.93, NSE = 0.91, Bias = 0.11 g C m−2 day−1 and RMSE = 1.04 g C m−2 day−1 for daily gross primary productivity, 0.94, 0.82, 0.24 g C m−2 day−1 and 0.72 g C m−2 day−1 for daily ecosystem respiration, and 0.79, 0.75, 0.14 g C m−2 day−1 and 0.89 g C m−2 day−1 for daily net ecosystem exchange, and slightly outperformed the GRNN and SVM models. In practical terms, however, the newly developed models (ANFIS and GRNN) are more robust and flexible, and have less parameters needed for selection and optimization in comparison with traditional ANN and SVM models. Consequently, they can be used as valuable tools to estimate forest carbon fluxes and fill the missing carbon flux data during the long-term EC measurements.

Implicit opinion analysis: Extraction and polarity labelling

Opinion words are crucial information for sentiment analysis. In some text, however, opinion words are absent or highly ambiguous. The resulting implicit opinions are more difficult to extract and label than explicit ones. In this paper, cutting‐edge machine‐learning approaches – deep neural network and word‐embedding – are adopted for implicit opinion mining at the snippet and clause levels. Hotel reviews written in Chinese are collected and annotated as the experimental data set. Results show the convolutional neural network models not only outperform traditional support vector machine models, but also capture hidden knowledge within the raw text. The strength of word‐embedding is also analyzed.