ELM Model Research Articles

Source credibility plays the central route: an elaboration likelihood model exploration in social media environment with demographic profile analysis

PurposeThis study aims at building a framework for the electronic word-of-mouth (eWOM) response under the social media environment. The elaboration likelihood model was adopted to explain how message source credibility and message appeal jointly influence the eWOM response process, while source credibility provides a central route and message appeal plays a peripheral route for information processing.Design/methodology/approachThis study used a scenario design to test the decision behavior in the Facebook environment through message content manipulation. A convenience sampling method was adopted in this study. We collected 203 valid questionnaires and tested this research model with LISREL 8.8. This study used a two-stage structural equation modeling data analysis method with LISREL 8.8, by which the measurement model was assessed through confirmatory factor analysis for the reliability and validity of the research model, and the causal relationship among factors was assessed through exploratory factor analysis .FindingsThe results showed that 53% variance of eWOM responses could be explained by message source credibility and emotional message appeal from the elaboration likelihood model perspective. Message source credibility plays a central role in the social media environment. The model was further tested with a demographic profile analysis for both gender and age. It is found that a female user is influenced by both source credibility and emotional appeal, but a male user is only influenced by message source credibility. The mature age group is more responsive to eWOM messages.Research limitations/implicationsThe sample might not represent all social networking sites (SNS) users. The participants represent a small segment of the Facebook population around the globe. Secondly, this research design could be improved by using more recreational messages to test the effects of message appeal and message source credibility. Thirdly, the mobile phone is a type of physical product rather than an experiential product. Future studies could try to identify the same eWOM determinants with different SNS functions, for example, the inbox message function. Similarly, Facebook users are allowed to use both text and pictures to disseminate promotional messages.Practical implicationsThis study provides an insight for SNS administrators regarding the determinants of driving more customer responses toward a message. Message source credibility and message appeal are identified as the antecedents for eWOM responses in SNS. Companies could make use of this finding to improve their marketing communication strategy in SNS. The finding can inform administrators of the importance of focusing on both customers’ psychological state and message attributes during the dissemination of promotional messages to improve the efficiency of the promotional effort. Companies aimed at receiving different types of eWOM responses in SNS may need to consider other factors for creating their promotional messages.Originality/valuePrevious studies have mainly identified factors influencing eWOM responses from the people-centered variables such as personal traits and social relationships. This study proposes that the eWOM response is a dual information processing process that can be explained by the ELM. When a user processes information in SNS, he follows both the central route and the peripheral route (i.e. source credibility and message appeal) which can influence the eWOM response. It is the first time that the source credibility is investigated as the central route in ELM model.

Efficient ELM Model With Parameter Optimization Using Pso Algorithms in the Prediction of Combustion Pressure Parameters of Dsi Engine Using Ethanol- Gasoline Blends

The present study focused mainly on developing PSO based ELM model to predict cylinder pressure associated parameters. Performance of PSO-ELM model then compared with ELM model to obtain its credential. For training and testing the models, data has been acquired through experiments on a Twin Spark Ignition (TSI) gasoline engine using EGB as fuel. The various operating variables are treated as input data whereas cylinder pressure associated parameters are treated as output data for the model. The result of the proposed modelling study indicated that PSO-ELM model has obtained the best performance with lowest value of MSE, MAPE (%) and hidden layer size as compared to ELM model. Hence PSO-ELM results in an efficient model structure with great generalization performance. Further, it is also observed that PSO-ELM takes more time as it calls for an iterative procedure for searching the optimal solution as compared to ELM, which takes only a single epoch.

SVM Model Against Telecom Card Fraud Using GA Optimised Ten-Fold Cross-Testing

The increased number of payment methods also makes it easier for personal information to be stolen by criminals, and for criminals to take over financial payment accounts and steal money. With trillions of bank card transactions occurring every day, Credit Card Fraud Detection (CCFD) is a serious challenge, so this paper predicts "whether or not fraud occurs" by using six types of machine learning models. For problem 1, firstly, "mean, maximum, minimum, median, variance, standard deviation, quartile" are calculated for each indicator; secondly, data cleaning is carried out, and the data set is found to be free of missing values and outliers. Then the data preprocessing work was carried out, min_max normalisation and z-score standardisation were performed on the data. After that, correlation analysis was carried out, and the first four indicators were classified as negative indicators and the last three as positive indicators according to the characteristics of the indicators themselves. It can be found by calculating the Pearson correlation coefficient value after two data processing. Using the coefficient of variation method to calculate the weight of the seven "influence whether fraud" indicators. Finally, BP neural network model, decision tree model, random forest classification model, ELM model, SVM model, logistic regression model are established. For Problem 2, the four models constructed in Problem 1 are solved; to solve the BP neural network model: the data set is divided into training set and testing set according to the ratio of 6:4, and the sigmod function is used as the activation function. For BP neural network, "output >0.5" is recorded as 1, i.e. fraudulent behaviour; "output <0.5" is recorded as 0, i.e. non-fraudulent behaviour. Adjusting the learning rate and the number of iterations, the optimal average mean square error after optimal gradient descent is smaller. To solve the SVM model, the data set is divided into ten groups using the improved ten-fold cross-test, with one group as the training set and nine groups as the validation set, so as to obtain the model with the highest accuracy and the corresponding training data, and then the genetic algorithm is used to search for the optimisation of the kernel parameters in the SVM model on this basis. To solve the decision tree model, the training set and prediction set are divided into 7:3 and solved, and the number of leaf nodes is optimised. Solve the random forest classification model, divided into training set and prediction set according to 7:3 and solved, for similar accuracy choose the random forest classifier when the decision tree is less.

A Study on the Performance Evaluation of the Convolutional Neural Network–Transformer Hybrid Model for Positional Analysis

In this study, we identified the different causes of odor problems and their associated discomfort. We also recognized the significance of public health and environmental concerns. To address odor issues, it is vital to conduct precise analysis and comprehend the root causes. We suggested a hybrid model of a Convolutional Neural Network (CNN) and Transformer called the CNN–Transformer to tackle this challenge and assessed its effectiveness. We utilized a dataset containing 120,000 samples of odor to compare the performance of CNN+LSTM, CNN, LSTM, and ELM models. The experimental results show that the CNN+LSTM hybrid model has an accuracy of 89.00%, precision of 89.41%, recall of 91.04%, F1-score of 90.22%, and RMSE of 0.28, with a large prediction error. The CNN+Transformer hybrid model had an accuracy of 96.21%, precision and recall of 94.53% and 94.16%, F1-score of 94.35%, and RMSE of 0.27, showing a low prediction error. The CNN model had an accuracy of 87.19%, precision and recall of 89.41% and 91.04%, F1-score of 90.22%, and RMSE of 0.23, showing a low prediction error. The LSTM model had an accuracy of 95.00%, precision and recall of 92.55% and 94.17%, F1-score of 92.33%, and RMSE of 0.03, indicating a very low prediction error. The ELM model performed poorly with an accuracy of 85.50%, precision and recall of 85.26% and 85.19%, respectively, and F1-score and RMSE of 85.19% and 0.31, respectively. This study confirms the suitability of the CNN–Transformer hybrid model for odor analysis and highlights its excellent predictive performance. The employment of this model is expected to be advantageous in addressing odor problems and mitigating associated public health and environmental concerns.

DDoS Attack Detection in WSN using Modified Invasive Weed Optimization with Extreme Learning Machine

Wireless sensor networks (WSN) are the wide-spread methodology for its distribution of the vast amount of devoted sensor nodes (SNs) that is employed for sensing the atmosphere and gather information. The gathered information was transmitted to the sink nodes via intermediate nodes. Meanwhile, the SN data are prone to the internet, and they are vulnerable to diverse security risks, involving distributed denial of service (DDoS) outbreaks that might interrupt network operation and compromises data integrity. In recent times, developed machine learning (ML) approaches can be applied for the discovery of DDoS attacks and accomplish security in WSN. To achieve this, this study presents a modified invasive weed optimization with extreme learning machine (MIWO-ELM) model for DDoS outbreak recognition in the WSN atmosphere. In the presented MIWO-ELM technique, an initial stage of data pre-processing is conducted. The ELM model can be applied for precise DDoS attack detection and classification process. At last, the MIWO method can be exploited for the parameter tuning of the ELM model which leads to improved performance of the classification. The experimental analysis of the MIWO-ELM method takes place using WSN dataset. The comprehensive simulation outputs show the remarkable performance of the MIWO-ELM method compared to other recent approaches.

Development and testing of a ground recognition system for tractor field operations

To overcome the problems of poor recognition accuracy, slow response speed, and unsuitable for farmland ground environment based on the traditional ground recognition method of vehicle mathematical model, this paper proposes a ground recognition system for tractor field operation based on wheel acceleration. A wheel acceleration sensor and data acquisition device are designed, and a ground recognition algorithm based on Principal Component Analysis - Genetic Algorithm optimization of an Extreme Learning Machine (PCA-GA-ELM) is investigated. The system can collect acceleration samples and extract statistical features in different frequency bands in real time according to the cycle of wheel rotation and then use the trained recognition model to recognize the ground type. In the actual operation process, this system only needs to collect the acceleration test data of one rotation of the tractor wheels to achieve the recognition of the ground. The test set data show that this system achieves 96 % discrimination accuracy, higher than the 87 % of the ELM model without genetic algorithm optimization and 92 % of the GA-BP neural network model. In addition, the real-time ground recognition test shows that the increase in operation speed will slightly reduce the accuracy of the recognition model, but the overall can still maintain 94–98 % accuracy, indicating that the system has good stability. This system can provide a reference for real-time speed adjustment, implement position, and other control parameters during tractor operation.

The Construction of the integration of ldeological and Political Curriculum for Graduate Students in Foreign Language Studies in the Context of New Liberal Arts and Big Data

Abstract Exploring the construction, of course, Civics of graduate students in foreign languages is to promote better the implementation of course, Civics in foreign languages. In this paper, in the context of the new liberal arts of big data, firstly, the method related to the sparrow search algorithm is described, and the parameters related to the sparrow search algorithm are optimized by using the good point set initialization and firefly update strategy. Then the basic principle of the extreme learning machine is given, and it is shown that the ELM model’s output weights are obtained using the inverse matrix solution. The ISSA-ELM algorithm model is elicited using the improved sparrow search algorithm with the extreme learning machine, and the ARE and RMSE performance validation is performed for this model using the UCI dataset. Finally, the ISSA-ELM algorithm was used to analyze and mine the indexes of the construction of the example of the postgraduate course Civics in foreign languages, including both teaching implementation and teaching content, using GZ University as an example. From the teaching implementation, the percentages of A, B, C and D evaluations are 16.12%, 18.44%, 18.12% and 47.32%, respectively. Regarding teaching content, the percentages of A, B, C, and D evaluations were 49.65%, 22.95%, 16.5%, and 10.89%, respectively. This indicates that the construction of the course Civics for graduate students in foreign language disciplines in the context of the new liberal arts is not optimistic, and effective reforms in teaching implementation and content are needed afterward.

SoftVein-WELM: A Weighted Extreme Learning Machine Model for Soft Biometrics on Palm Vein Images

Contactless biometric technologies such as palm vein recognition have gained more relevance in the present and immediate future due to the COVID-19 pandemic. Since certain soft biometrics like gender and age can generate variations in the visualization of palm vein patterns, these soft traits can reduce the penetration rate on large-scale databases for mass individual recognition. Due to the limited availability of public databases, few works report on the existing approaches to gender and age classification through vein pattern images. Moreover, soft biometric classification commonly faces the problem of imbalanced data class distributions, representing a limitation of the reported approaches. This paper introduces weighted extreme learning machine (W-ELM) models for gender and age classification based on palm vein images to address imbalanced data problems, improving the classification performance. The highlights of our proposal are that it avoids using a feature extraction process and can incorporate a weight matrix in optimizing the ELM model by exploiting the imbalanced nature of the data, which guarantees its application in realistic scenarios. In addition, we evaluate a new class distribution for soft biometrics on the VERA dataset and a new multi-label scheme identifying gender and age simultaneously. The experimental results demonstrate that both evaluated W-ELM models outperform previous existing approaches and a novel CNN-based method in terms of the accuracy and G-mean metrics, achieving accuracies of 98.91% and 99.53% for gender classification on VERA and PolyU, respectively. In more challenging scenarios for age and gender–age classifications on the VERA dataset, the proposed method reaches accuracies of 97.05% and 96.91%, respectively. The multi-label classification results suggest that further studies can be conducted on multi-task ELM for palm vein recognition.

Short-term streamflow modeling using data-intelligence evolutionary machine learning models

Accurate streamflow prediction is essential for efficient water resources management. Machine learning (ML) models are the tools to meet this need. This paper presents a comparative research study focusing on hybridizing ML models with bioinspired optimization algorithms (BOA) for short-term multistep streamflow forecasting. Specifically, we focus on applying XGB, MARS, ELM, EN, and SVR models and various BOA, including PSO, GA, and DE, for selecting model parameters. The performances of the resulting hybrid models are compared using performance statistics, graphical analysis, and hypothesis testing. The results show that the hybridization of BOA with ML models demonstrates significant potential as a data-driven approach for short-term multistep streamflow forecasting. The PSO algorithm proved superior to the DE and GA algorithms in determining the optimal hyperparameters of ML models for each step of the considered time horizon. When applied with all BOA, the XGB model outperformed the others (SVR, MARS, ELM, and EN), best predicting the different steps ahead. XGB integrated with PSO emerged as the superior model, according to the considered performance measures and the results of the statistical tests. The proposed XGB hybrid model is a superior alternative to the current daily flow forecast, crucial for water resources planning and management.

Determination of extensibility and toughness of wheat-flour dough based on bubbles blown by sheeted dough and airflow-3D imaging technique

The resistance strength (toughness) and extensibility of dough are closely related to the quality of the dough product. In this study, the toughness and extensibility of dough were detected using an airflow-structured light 3D imaging technique combine with bubbles blown out of sheeted dough. The spatial deformation characteristics and point cloud features of each point cloud image were determined using the point cloud data processing algorithms. The frame, height, volume, surface area, projected area of three planes, and three point cloud features corresponding to the maximum height of the bubble were taken as the extracted features. A total of eight features were selected, which were consequently concentrated in the first three principal components (PCs). The first three PCs were fed into three different prediction models. The ELM model achieved a relatively higher prediction accuracy than the other two models. For toughness and extensibility, Rp were 9092 and 0.8950, respectively.

Underwater Image Color Constancy Calculation with Optimized Deep Extreme Learning Machine Based on Improved Arithmetic Optimization Algorithm

To overcome the challenges posed by the underwater environment and restore the true colors of marine objects’ surfaces, a novel underwater image illumination estimation model, termed the iterative chaotic improved arithmetic optimization algorithm for deep extreme learning machines (IAOA-DELM), is proposed. In this study, the gray edge framework is utilized to extract color features from underwater images, which are employed as input vectors. To address the issue of unstable prediction results caused by the random selection of parameters in DELM, the arithmetic optimization algorithm (AOA) is integrated, and the search segment mapping method is optimized by using hidden layer biases and input layer weights. Furthermore, an iterative chaotic mapping initialization strategy is incorporated to provide AOA with a better initial search proxy. The IAOA-DELM model computes illumination information based on the input color vectors. Experimental evaluations conducted on actual underwater images demonstrate that the proposed IAOA-DELM illumination correction model achieves an accuracy of 96.07%. When compared to the ORELM, ELM, RVFL, and BP models, the IAOA-DELM model exhibits improvements of 6.96%, 7.54%, 8.00%, and 8.89%, respectively, making it the most effective among the compared illumination correction models.

Daily tourism forecasting through a novel method based on principal component analysis, grey wolf optimizer, and extreme learning machine

AbstractAccurate forecasting tourism demand is crucial for improving the economic benefits of tourist attractions, but it is a challenging task. In this paper, we propose an effective daily tourism forecast model, principal component analysis‐grey wolf optimizer‐extreme learning machine (PCA‐GWO‐ELM), based on Baidu index data, holiday data, and weather data. Our model uses PCA to reduce the dimensionality of the data and employs the GWO to optimize the number of neural networks in the hidden layer of the ELM model, improving its forecast performance. We conduct an empirical study using the collected tourist data of Mount Siguniang. The results show that the proposed hybrid forecasting model outperforms other models in daily tourism demand forecasting, making it a potential candidate method for practitioners and researchers studying tourism demand forecasting.

Prediction of 316 stainless steel low-cycle fatigue life based on machine learning

The low-cycle fatigue life of 316 stainless steel is a significant basis for safety assessment. Usually, many factors affect the low-cycle fatigue life of stainless steel, and the relationship between the influencing factors and fatigue life is complicated and nonlinear. Therefore, it is hard to predict fatigue life using the traditional empirical formula. Based on this, a machine learning algorithm is proposed. In this paper, based on the large amount of existing experimental data, machine learning methods are used to predict the low circumferential fatigue life of 316 stainless steel. The results show that the prediction accuracy of nu-SVR and ELM models is high and can meet engineering needs.

Deep Extreme Learning Machines Based Two-Phase Spatiotemporal Modeling for Distributed Parameter Systems

Accurate and robust modeling of complex distributed parameter systems (DPSs) is a challenge for three reasons: 1) they have infinite-dimensional characteristics; 2) they are time/space coupled; and 3) there are model uncertainties. In this article, a two-phase spatiotemporal (S/T) modeling framework based on deep extreme learning machine (DELM) is proposed for DPSs. The modeling process consists of two S/T models in two phases: Phase I: a DELM model and Phase II: a Karhunen–Loève (KL) based ELM (KL-ELM) model. In phase I, the DELM model is constructed by combing the multilayer ELM (ML-ELM), ELM, and kernel-based ELM (K-ELM) to approximate the dominant S/T dynamics of DPSs. Since DPSs have an infinite-dimensional characteristic that can hardly be handled directly, ML-ELM is first employed to transform the infinite-dimensional systems into finite-dimensional systems. Then, the ELM model is adopted to further approximate the finite-dimensional systems to ensure the model can predict future dynamic behavior. Finally, the K-ELM is used to reconstruct the infinite-dimensional systems, which can be considered as the inverse process of ML-ELM. Thus, the final DELM model can be used for prediction in both space and time directions. In phase II, a KL-ELM model is constructed to compensate for modeling errors caused by reconstruction error or unknown nonlinear dynamics. By integrating the obtained DELM and KL-ELM models, the proposed two-phase S/T model can be constructed. Experiments on a typical industrial thermal process verified that the proposed method may work better in complex DPSs.

Combining BPSO and ELM Models for Inferring Novel lncRNA-Disease Associations

It has been widely known that long non-coding RNA (lncRNA) plays an important role in gene expression and regulation. However, due to a few characteristics of lncRNA (e.g., huge amounts of data, high dimension, lack of noted samples, etc.), identifying key lncRNA closely related to specific disease is nearly impossible. In this paper, the authors propose a computational method to predict key lncRNA closely related to its corresponding disease. The proposed solution implements a BPSO based intelligent algorithm to select possible optimal lncRNA subset, and then uses ML-ELM based deep learning model to evaluate each lncRNA subset. After that, wrapper feature extraction method is used to select lncRNAs, which are closely related to the pathophysiology of disease from massive data. Experimentation on three typical open datasets proves the feasibility and efficiency of our proposed solution. This proposed solution achieves above 93% accuracy, the best ever.

SERIAL MEDIATION OF PERCEIVED USEFULNESS AND EWOM ADOPTION IN VIRTUAL COMMUNITIES AND THE MODERATING EFFECT OF GENDER

Purpose – This study analyzes the adoption behavior of eWOM information from the consumer’s perspective. In virtual communities, this study examines the serial mediation of perceived usefulness and adoption of eWOM between eWOM characteristics (credibility, quality, and vivacity) and the intention to visit a tourist destination and gender as a moderator. This study makes a significant theoretical and practical contribution by the purpose of an integrative model, according to the ELM model, and by examining the moderating effect of gender. Design/Methodology/Approach – This study tests the hypothesis using an experimental scenario simulation method. Signals embedded in various components of the eWOM (stimuli/ scenarios) were used, such as interactivity with the message (Like number, comment, sharing) or the content of the message (Text, Visual, Video). The new model (based on the ELM model) was validated by PLS-SEM based on an online survey of 548 members of the virtual consumption communities where content shared is about tourism and hospitality, tourism experiences, and recommendations of Algerian tourist destinations. Findings – The results confirm that perceived usefulness and adoption are two serial mediators between the relationship between eWOM characteristics and visit intention. Finally, gender moderates the indirect effect between eWOM quality and the intention to visit. Originality of the research – This study proposes to develop an integrative model by testing the serial mediating effects of perceived usefulness and information adoption for the first time regarding the influence of the three eWOM characteristics on behavioral intention and investigates the role of gender as a moderator.

Research on deformation prediction of deep foundation pit excavation based on GWO-ELM model

<abstract> <p>Given the complex nonlinear problem between the control and prediction of the surrounding surface settlement deformation caused (GWO), the GWO-ELM deep foundation pit excavation deformation prediction model was proposed. Extreme learning machine and Grey Wolf optimization algorithm combining training and predicting land subsidence. Based on MIDAS GTS NX software, we established a finite element simplified model for deep foundation pit construction, conducted structural calculations, and utilized the Grey Wolf optimization algorithm to optimize the deep foundation pit excavation and its influencing factors, input weights, and hidden layer thresholds in the ELM neural network. Taking the deep foundation pit project of Baoding Automobile Science and Technology Industrial Park as an example, the actual monitoring value is compared with the simulated value, verifying the model's accuracy. The number of soil nails in the finite element model, the excavation depth, the settlement of surrounding buildings and other factors are taken as the input factors of the prediction model. The DB-2 surface settlement of the monitoring point in the finite element model is taken as the output factor of the prediction model. The predicted value of the GWO-ELM model was compared with that of the ELM model. We draw three main conclusions from the results. First, the surface settlement of a bottomless foundation pit can be predicted in advance by using finite element software and the distribution law of surface settlement and horizontal displacement is consistent with the measured values. Second, the Grey Wolf optimization algorithm optimizes the input weights and thresholds in the extreme learning machine neural network. The GWO-ELM prediction model has good generalization ability, can effectively reduce human errors and can improve the accuracy of the prediction model. Third, through practical engineering verification, the average absolute error of the GWO-ELM model is 0.26145, the mean square error is 0.31258 and the R<sup>2</sup> is 0.98725, all of which are superior to the ELM model and are an effective method for predicting deformation and settlement of deep foundation pit excavation.</p> </abstract>

Quantitative analysis of Cd based on the stress effect of minerals in rice by laser-induced breakdown spectroscopy.

Cadmium (Cd) is a highly toxic heavy metal that can accumulate in the food chain, posing a significant threat to human health. One of the key food sources through which Cd is often observed is rice. Therefore, determining heavy metals in rice is essential to assess the risk status of rice. Laser-induced breakdown spectroscopy (LIBS) has the advantages of simple sample preparation and fast analysis, which is expected to achieve real-time and rapid detection of rice. In this work, 40 naturally matured rice samples growing from the area that is possibly contaminated with Cd were collected to determine the Cd reference content in rice by graphite furnace atomic absorption spectroscopy as recommended by the Chinese National Standard. LIBS spectral acquisition and analysis are adopted as well. The Cd characteristic spectral lines were selected to predict the Cd content directly using PCA, PLSR, and ELM models, and the coefficient of determination (R2) of the models' training and prediction sets was 0.9278, 0.8920; 0.9036, 0.9771; 0.7940, and 0.8409, respectively. Further, based on the Cd stress effect in rice, the spectra of elements Mn, Mg, K, and Na with highly significant and significant correlation with Cd were selected and coupled with the Cd characteristic spectra to form a new matrix of the same size for quantitative analysis. Based on the stress effect, R2 of models' training and prediction sets was improved to 0.9786, 0.9753; 0.9395, 0.9900; 0.9798, and 0.9927, respectively. It is demonstrated that combining the stress effect when using LIBS for quantitative analysis of Cd in rice reduces the overfitting and further improves the model's prediction accuracy. This work indicates that using LIBS combined with suitable mathematical models to predict the Cd content of naturally matured rice based on stress effects in rice is feasible. It is promising to evaluate the safety of rice by analyzing LIBS spectra.

Simulated Annealing with Deep Learning Based Tongue Image Analysis for Heart Disease Diagnosis

Tongue image analysis is an efficient and non-invasive technique to determine the internal organ condition of a patient in oriental medicine, for example, traditional Chinese medicine (TCM), Japanese traditional herbal medicine, and traditional Korean medicine (TKM). The diagnosis procedure is mainly based on the expert's knowledge depending upon the visual inspection comprising color, substance, coating, form, and motion of the tongue. But conventional tongue diagnosis has limitations since the procedure is inconsistent and subjective. Therefore, computer-aided tongue analyses have a greater potential to present objective and more consistent health assessments. This manuscript introduces a novel Simulated Annealing with Transfer Learning based Tongue Image Analysis for Disease Diagnosis (SADTL-TIADD) model. The presented SADTL-TIADD model initially pre-processes the tongue image to improve the quality. Next, the presented SADTL-TIADD technique employed an EfficientNet-based feature extractor to generate useful feature vectors. In turn, the SA with the ELM model enhances classification efficiency for disease detection and classification. The design of SA-based parameter tuning for heart disease diagnosis shows the novelty of the work. A wide-ranging set of simulations was performed to ensure the improved performance of the SADTL-TIADD algorithm. The experimental outcomes highlighted the superior of the presented SADTL-TIADD system over the compared methods with maximum accuracy of 99.30%.

Improved support vector machine classification for imbalanced medical datasets by novel hybrid sampling combining modified mega-trend-diffusion and bagging extreme learning machine model.

To handle imbalanced datasets in machine learning or deep learning models, some studies suggest sampling techniques to generate virtual examples of minority classes to improve the models' prediction accuracy. However, for kernel-based support vector machines (SVM), some sampling methods suggest generating synthetic examples in an original data space rather than in a high-dimensional feature space. This may be ineffective in improving SVM classification for imbalanced datasets. To address this problem, we propose a novel hybrid sampling technique termed modified mega-trend-diffusion-extreme learning machine (MMTD-ELM) to effectively move the SVM decision boundary toward a region of the majority class. By this movement, the prediction of SVM for minority class examples can be improved. The proposed method combines α-cut fuzzy number method for screening representative examples of majority class and MMTD method for creating new examples of the minority class. Furthermore, we construct a bagging ELM model to monitor the similarity between new examples and original data. In this paper, four datasets are used to test the efficiency of the proposed MMTD-ELM method in imbalanced data prediction. Additionally, we deployed two SVM models to compare prediction performance of the proposed MMTD-ELM method with three state-of-the-art sampling techniques in terms of geometric mean (G-mean), F-measure (F1), index of balanced accuracy (IBA) and area under curve (AUC) metrics. Furthermore, paired t-test is used to elucidate whether the suggested method has statistically significant differences from the other sampling techniques in terms of the four evaluation metrics. The experimental results demonstrated that the proposed method achieves the best average values in terms of G-mean, F1, IBA and AUC. Overall, the suggested MMTD-ELM method outperforms these sampling methods for imbalanced datasets.