Predicting Intentions of Students for Master Programs Using a Chaos-Induced Sine Cosine-Based Fuzzy K-Nearest Neighbor Classifier

Lin, Aiju; Wu, Quanquan; Heidari, Ali Asghar; Xu, Yanmei; Chen, Huiling; Wang, Geng; Li, Yuping; Li, Chengye

doi:10.1109/access.2019.2918026

Cited by 96 publications

(41 citation statements)

References 52 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Finally, the optimal FKNN classifier is taken to determine whether the specific patient is severe or nonsevere. The commonly used 10-fold cross-validation (CV) scheme is used to divide the data and obtain more accurate and unbiased experimental results, often adopted by many studies [67]- [74].…”

Section: Hho-fknn Methodsmentioning

confidence: 99%

Diagnosing Coronavirus Disease 2019 (COVID-19): Efficient Harris Hawks-Inspired Fuzzy K-Nearest Neighbor Prediction Methods

Zhu

et al. 2021

IEEE Access

Self Cite

View full text Add to dashboard Cite

This study is devoted to proposing a useful intelligent prediction model to distinguish the severity of COVID-19, to provide a more fair and reasonable reference for assisting clinical diagnostic decision-making. Based on patients' necessary information, pre-existing diseases, symptoms, immune indexes, and complications, this article proposes a prediction model using the Harris hawks optimization (HHO) to optimize the Fuzzy K-nearest neighbor (FKNN), which is called HHO-FKNN. This model is utilized to distinguish the severity of COVID-19. In HHO-FKNN, the purpose of introducing HHO is to optimize the FKNN's optimal parameters and feature subsets simultaneously. Also, based on actual COVID-19 data, we conducted a comparative experiment between HHO-FKNN and several well-known machine learning algorithms, which result shows that not only the proposed HHO-FKNN can obtain better classification performance and higher stability on the four indexes but also screen out the key features that distinguish severe COVID-19 from mild COVID-19. Therefore, we can conclude that the proposed HHO-FKNN model is expected to become a useful tool for COVID-19 prediction. INDEX TERMSCOVID-19, coronavirus, fuzzy K-nearest neighbor, Harris hawk optimization, disease diagnosis, feature selection. I. INTRODUCTION Coronavirus disease 2019 (COVID-19) is a highly contagious viral disease, and the World Health Organization (WHO) declared that the COVID-19 was an international public health emergency [1], [2]. First described COVID-19 in December 2019 in Wuhan, Hubei Province, China. The ongoing outbreak of COVID-19 is affecting multiple countries in the world [1]. Until Mar 11th, 2020, The associate editor coordinating the review of this manuscript and approving it for publication was Juan Wang . 118,326 cases of COVID-19 were diagnosed worldwide, including 80,955 cases in China and 37,371 cases outside China. Additionally, 4,292 deaths have been triggered by COVID-19 [3]. Many countries are facing increased pressures on health care resources. Up to now, a great deal of studies is focused on using traditional statistical methods to identify risk factors of COVID-19 patients. As an example, older age, pre-existing diseases, abnormal liver function, and T-lymphocyte count were correlated closely with COVID-19 progression and prognosis [4]-[6]. However, traditional statistical methods could not rapidly identify changes

show abstract

Section: Hho-fknn Methodsmentioning

confidence: 99%

Diagnosing Coronavirus Disease 2019 (COVID-19): Efficient Harris Hawks-Inspired Fuzzy K-Nearest Neighbor Prediction Methods

Zhu

et al. 2021

IEEE Access

Self Cite

View full text Add to dashboard Cite

show abstract

“…Since its inception, SCA has been extensively utilized in various applications such as wind speed forecast [76], time series prediction [77], prediction of the intention of students for postgraduate entrance examination [78], and prediction of the entrepreneurial intention of students [79]. Moreover, many improved SCA variants have been proposed to improve its performance.…”

Section: Olscamentioning

confidence: 99%

“…In order to study the performance of the proposed strategy, some competitive MAs, including the MSCA [83], OBSCA, chaos enhanced SCA (CESCA) [78], bat algorithm (BA) [92], MFO, firefly algorithm (FA) [93], PSO and SCA are made a comparison on 23 well-known benchmark functions. The full parameter values of these involved algorithms are reported in Table 2.…”

Section: A Benchmark Function Validationmentioning

confidence: 99%

Evaluation of Sino Foreign Cooperative Education Project Using Orthogonal Sine Cosine Optimized Kernel Extreme Learning Machine

Zhu

Zhao

et al. 2020

IEEE Access

Self Cite

View full text Add to dashboard Cite

This study aims to propose an efficient evaluation model for Sino foreign cooperative education projects, which can offer a reasonable reference for universities to deepen reform and innovation of education and further enhance the level of international education. The core engine of the model is the kernel extreme learning machine (KELM) model integrated with orthogonal learning (OL) strategy optimization. The introduction of the OL mechanism is to further strengthen the optimization capabilities of the basic SCA, which is devoted to promoting the KELM model to select the optimal parameter combination and feature subset and further enhance the KELM evaluation capability of Sino foreign cooperative education projects. To examine the performance of the proposed method, OLSCA is evaluated on 23 benchmark problems, comparison with eight other well-known methods. The experimental results have shown that the proposed OLSCA is prominently superior to existing methods on most functional problems. Meantime, OLSCA-KELM is compared against other machine learning approaches in dealing with the evaluation of education projects of Sino foreign cooperation. The simulation results illustrate that the presented OLSCA-KELM obtains better performance of classification and higher stability on all four indicators. Therefore, it is evident that the presented OLSCA-KELM can be an effective solution for the evaluation of Sino foreign cooperative education projects. INDEX TERMS Sine cosine algorithm, swarm intelligence, sino foreign cooperative education project, Kernel extreme learning machine, parameter optimization. HUILING CHEN received the Ph.D. degree from the Department of Computer Science and Technology, Jilin University, China. He is currently an Associate Professor with the College of Computer Science and Artificial Intelligence, Wenzhou University, China. He has published more than 100 articles in international journals and conference proceedings, including Information Sciences, Pattern Recognition, Future Generation Computer System, Expert Systems with Applications, Knowledge-Based Systems, Neurocomputing, PAKDD, and among others. His current research interests include machine learning and data mining, as well as their applications to medical diagnosis and bankruptcy prediction. He is also a Reviewer of many journals such as Applied Soft Computing, Artificial Intelligence in Medicine, Knowledge-Based Systems, and Future Generation Computer System. He has been serving as an Associate Editor for IEEE ACCESS.

show abstract

“…We also used machine learning models to perform comparison between the results if machine learning models and the proposed DS-MLP. Five machine learning models such as logistic regression (LR) [36], [37], random forest (RF) [38], [39], decision tree (DT) [40], support vector machine (SVM) [41], K nearest neighbour (KNN) [42] and Gaussian Naive Bayes (GNB) [43] algorithms are used for this purpose. We use RF with 300 n_estimators which means that 300 decision trees are constructed by RF on each example to give the predictions and then perform majority voting between 300 predictions to make the final prediction.…”

Section: B Comparison With Other Machine Learning Modelsmentioning

confidence: 99%

Sensor-Based Human Activity Recognition Using Deep Stacked Multilayered Perceptron Model

et al. 2020

View full text Add to dashboard Cite

The recent development of machines exhibiting intelligent characteristics involves numerous techniques including computer hardware and software architecture development. Many different hardware devices, wearable sensors, machine learning, and deep learning model implementations are being applied in human activity recognition (HAR) applications in recent times. However, to develop high accuracy classification systems for activity recognition using low-cost hardware technology is of significant importance. To achieve this goal this study uses sensor data from two low-cost sensors, gyroscope and accelerometer along with the implementation of an Artificial Neural Network (ANN) based deep learning model for HAR. In particular, Deep Stacked Multilayered Perceptron (DS-MLP) has been proposed. In the implementation of DS-MLP, an ANN model has been used as a meta-learner while five MLP models have been used as base-learners. In this study, these base-learners and meta-learner have been combined using a stack ensemble technique. The performance evaluations have been done first on the applicability of individual base-models followed by the application of DS-MLP, the results prove the high accuracy of 97.3% and 99.4% for heterogeneous datasets used for testing. The performance of the proposed DS-MLP models has been compared to some existing machine learning classifiers and several state-of-the-art activity recognition systems. The comparative result analysis also proves that the proposed system performed better than these classification approaches in terms of important performance metrics such as accuracy, precision, recall, F-score, Cohen's Kappa, and Mathew correlation coefficient.

show abstract

Predicting Intentions of Students for Master Programs Using a Chaos-Induced Sine Cosine-Based Fuzzy K-Nearest Neighbor Classifier

Cited by 96 publications

References 52 publications

Diagnosing Coronavirus Disease 2019 (COVID-19): Efficient Harris Hawks-Inspired Fuzzy K-Nearest Neighbor Prediction Methods

Diagnosing Coronavirus Disease 2019 (COVID-19): Efficient Harris Hawks-Inspired Fuzzy K-Nearest Neighbor Prediction Methods

Evaluation of Sino Foreign Cooperative Education Project Using Orthogonal Sine Cosine Optimized Kernel Extreme Learning Machine

Sensor-Based Human Activity Recognition Using Deep Stacked Multilayered Perceptron Model

Contact Info

Product

Resources

About