Zeinab Hassani | Institute for Advanced Studies in Basic Science (IASBS) (original) (raw)

Papers by Zeinab Hassani

Research paper thumbnail of Intelligent application for Heart disease detection using Hybrid Optimization algorithm

International Symposium on Algorithms and Computation, Jun 1, 2019

Prediction of heart disease is very important because it is one of the causes of death around the... more Prediction of heart disease is very important because it is one of the causes of death around the world. Moreover, heart disease prediction in the early stage plays a main role in the treatment and recovery disease and reduces costs of diagnosis disease and side effects it. Machine learning algorithms are able to identify an effective pattern for diagnosis and treatment of the disease and identify effective factors in the disease. this paper is investigated a new hybrid algorithm of Whale Optimization and Dragonfly algorithm using a machine learning algorithm. the hybrid algorithm employs a Support Vector Machine algorithm for effective Prediction of heart disease. Proposed method is evaluated by Cleveland standard heart disease dataset. The experimental result indicates that the SVM accuracy of 88.89 % and nine features are selected in this respect.

Research paper thumbnail of Prediction and determining the effective factors on the survival transplanted kidney for five-year in imbalanced data by the meta-heuristic approach and machine learning

پردازش علائم و دادهها, Mar 1, 2019

Research paper thumbnail of The Application of an Evolutionary Model using Fuzzy Logic on Health Literacy Data

Health education & health promotion, Jul 1, 2019

Analyzing diabetes datasets using data ... [9] Data-mining technologies for diabetes: A systemati... more Analyzing diabetes datasets using data ... [9] Data-mining technologies for diabetes: A systematic ... [10] Systematic review of data mining applications in patient-centered mobile-based information ... [11] Privacy preserving distributed association rule mining approach on vertically partitioned healthcare ... [12] Prediction of benign and malignant breast cancer using data mining ... [13] Application of data mining: Diabetes health care in young and ... [14] Breast cancer diagnosis via data mining: performance analysis of seven different ... [15] Data mining techniques and applications-a decade review from 2000 to ... [16] Data mining and medical world: Breast cancers' diagnosis, treatment, prognosis and ... [17] Data mining application for exploring the relationship between addiction and ... [18] Data mining algorithms and techniques in mental health: A systematic ... [19] Applying data mining techniques in ... [20] Particle swarm optimization: A survey of historical and recent developments with hybridization ... [21] A comprehensive survey on particle swarm optimization algorithm and its ... [22] Particle swarm ... [23] Compressed kNN: K-nearest neighbors with data ... [24] Application of the weighted k-nearest neighbor algorithm for short-term load ... [25] Fuzzy k-nearest neighbor method to classify data in a closed ... [26] Hybrid intelligent system for cardiac arrhythmia classification with fuzzy k-nearest neighbors and neural networks combined with a fuzzy ... [27] Health literacy status and understanding of the prescription instructions in diabetic ... [28] A new adaptive testing algorithm for shortening health literacy ... Aims Health literacy (HL) is the main factor shows health literate level of people in a certain society. Discovering and understanding affective factors on HL level could lead experts to improve these factors in the target community. This study aimed to Health Literacy classification of population and find a major component with data mining approaches. Instruments and Methods In this paper, we have acquired more details about major factors on the health literacy level of target society by assessing evolutionary methods. We benefit of Particle Swarm Optimization (PSO) and KNN and fuzzy KNN algorithm for classification and use wrapper technique for feature selection by our model. Feature selection are done as weighted features and selects the most effective features of health literacy. Our proposed model evaluates a data set of Health Literacy by two classifiers with/without fuzzy logic. Applied data set is a real data gathered from a descriptive-analytic cross-sectional study on adult population include 2133 record with 74 attributes in 2016 at South Khorasan province. We have gained effective factors on HL level of the population according to regions and total population without using any statistical analysis tools with the lowest human interference by an evolutionary method. Findings Proposed model have found effective factors on the health literacy level of population in South Khorasan province. Results are obtained 92.02% accuracy for the total population and 97.99% for regions population. Conclusion Simulations demonstrate the evolutionary method is a suitable way for extracting results from health data sets and also shows the superiority of the proposed method.

Research paper thumbnail of An Artificial Predictive Modeling Framework for Automatically Detecting Problematic Use of Internet

International journal of computer applications, May 17, 2018

The Internet is one of the most influential new communications technologies that have been affect... more The Internet is one of the most influential new communications technologies that have been affected both social and health aspects of users' lives. Despite many advantages and its positive pointes in communication, the excessive use of Internet make a serious danger that has adverse impacts on overall health. The inability of individuals to control the Internet use has been defined as Internet Addiction (IA). There are a lot of studies on IA over the topics of diagnosis, phenomenology, epidemiology, and treatment based on statistical analysis, but a few research works are conducted by machine learning techniques. So our research focuses on diagnosing and counseling to prevent IA by developing prediction models based on ensemble method with machine learning algorithms and finding the most important risk factors in diagnosing the status of users' IA. Experiment results demonstrate that this hybrid machine learning model by considering students field and location along with items 1, 3, 4, 5, 10, 12, 14, 15, 19, 20 from Internet Addiction Test (IAT) as the most important risk factors can identify the status of users' IA with 99.75% accuracy attains a performance superior to traditional single classifier systems.

Research paper thumbnail of On the facility location problem: One-round weighted Voronoi game

Social Science Research Network, 2020

Research paper thumbnail of H-BwoaSvm: A Hybrid Model for Classification and Feature Selection of Mammography Screening Behavior Data

Journal of AI and Data Mining, Apr 1, 2020

Breast cancer is one of the most common cancer in the world. An early detection of cancers causes... more Breast cancer is one of the most common cancer in the world. An early detection of cancers causes a significant reduction in the morbidity rate and treatment costs. Mammography is a known effective diagnosis method of breast cancer. A way for mammography screening behavior identification is women's awareness evaluation for participating in the mammography screening programs. Today, intelligence systems could identify the main factors involved in a specific incident. These could help the experts a wide range of areas, specially health scopes such as prevention, diagnosis, and treatment. In this paper, we use a hybrid model called H-BwoaSvm BWOA is used for detecting the effective factors involved in the mammography screening behavior and SVM for classification. Our model is applied on a data-set which is collected from a segmental analytical descriptive study on 2256 women. The proposed model is operated on a data-set with 82.27% and 98.89% accuracy and selects the effective features on the mammography screening behavior.

Research paper thumbnail of Credit Risk Assessment Using Learning Algorithms for Feature Selection

Fuzzy Information and Engineering, Oct 1, 2020

Firefly algorithm is one of the latest outstanding bio-inspired algorithms, which could be manipu... more Firefly algorithm is one of the latest outstanding bio-inspired algorithms, which could be manipulated in solving continuous or discrete optimisation problems. In this context, we have utilised the firefly algorithm accompanied by five well-known models of feature selection classifiers to have an accurate estimation of risk, and further to improve the interpret-ability of credit card prediction. One of the significant challenges in the real-world datasets is how to select features. As most of the datasets are unbalanced, the selection of features turns to the maximum class of data that is not fair. To overcome this issue, we have balanced the data using the SMOTE method. Our experimental results on four datasets show that balancing data has increased accuracy. In addition, using a hybrid firefly algorithm, the optimal combination of features that predicts the target class label is achieved. The selected features by the proposed method besides been reduced can represent both majority and minority classes.

Research paper thumbnail of A System for Diagnosis of Coronary Artery Disease based on Neural Networks and Machine Learning Algorithms

International journal of computer applications, Sep 17, 2018

Today, computer aided systems play an important role in various fields of medical science such as... more Today, computer aided systems play an important role in various fields of medical science such as diagnosis and treatment of diseases; therefore, selected tools should minimize error and maximize the confidence. In this study, considering the importance of cardiovascular disease in the world, the coronary artery disease is diagnosed by neural networks and machine learning algorithms. The proposed system employs three types of artificial neural networks, decision tree and Adaboost algorithm to distinguish people who suffer from heart disease and the healthy individuals using Cleveland's dataset. Among these algorithms, the multilayer perceptron neural network has the best performance and is able to predict coronary artery disease with the accuracy, sensitivity and specificity of 94.53%, 86.77%, and 99.39%, respectively. The superiority of the proposed system is obvious comparing to other existing studies because it diagnoses the disease with higher accuracy, sensitivity and more reliability.

Research paper thumbnail of Prediction of the Survival of Kidney Transplantation with imbalanced Data Using Intelligent Algorithms

DOAJ (DOAJ: Directory of Open Access Journals), Aug 1, 2018

Kidney transplantation is one of the effective post-dialysis treatment methods for patients with ... more Kidney transplantation is one of the effective post-dialysis treatment methods for patients with chronic renal failure in the world. Most medical data are imbalanced and the output of algorithms is inefficient with imbalanced data. The aim of this study is to predict the two-year survival rate of kidney transplant patients and provide a more accurate model. We evaluate the data of renal transplant patients in Afzalipour Medical Education Center 2006-2010, Kerman, Iran. Survival prediction of kidney transplantation with MLP and RBF neural networks with two methods of sampling and investigating the factors affecting the survival of kidney transplant in renal transplant patients is considered by the binary particle optimization algorithm and nearest neighbor algorithm. Accuracy of the results can be increased by using the oversampling method in imbalanced medical data, and radial base network model is a suitable model for predicting the survival of kidney transplant patients.

Research paper thumbnail of Hybrid Algorithms of Whale optimization algorithm and k-nearest neighbor to Predict the liver disease

EAI endorsed transactions on context-aware systems and applications, May 23, 2019

Liver Disease is one of the most common diseases which can be prevented by early diagnosis and up... more Liver Disease is one of the most common diseases which can be prevented by early diagnosis and up-todate treatment. Advances in machine learning and intelligence techniques have led to the effective diagnosis and prediction of diseases to improve the treatment of patients and reduce the cost of treatment. Whale Optimization Algorithm is a swarm intelligent technique, inspired by the social behavior of whales. One of the effective classification algorithms is K-Nearest Neighbor which is employed for pattern recognition. This paper was designed to investigate the prediction of Liver Disease using a hybrid algorithm including KNN and WOA. In order to evaluate the efficiency of hybrid algorithm, two datasets of liver disease including BUPA and ILPD were used. The results showed that 81.24% and 91.28% of accuracy was gained by the proposed algorithm for BUPA and ILPD, respectively. Experimental results showed that the hybrid WON-KNN is a better classifier to predict the liver diseases

Research paper thumbnail of Credit Risk Assessment Using Learning Algorithms for Feature Selection

Fuzzy Information and Engineering, 2020

Firefly algorithm is one of the latest outstanding bio-inspired algorithms, which could be manipu... more Firefly algorithm is one of the latest outstanding bio-inspired algorithms, which could be manipulated in solving continuous or discrete optimisation problems. In this context, we have utilised the firefly algorithm accompanied by five well-known models of feature selection classifiers to have an accurate estimation of risk, and further to improve the interpret-ability of credit card prediction. One of the significant challenges in the real-world datasets is how to select features. As most of the datasets are unbalanced, the selection of features turns to the maximum class of data that is not fair. To overcome this issue, we have balanced the data using the SMOTE method. Our experimental results on four datasets show that balancing data has increased accuracy. In addition, using a hybrid firefly algorithm, the optimal combination of features that predicts the target class label is achieved. The selected features by the proposed method besides been reduced can represent both majority and minority classes.

Research paper thumbnail of Hybrid Particle Swarm Optimization with Ant-Lion Optimization: Experimental in Benchmarks and Applications

Journal of AI and Data Mining, Nov 6, 2021

A major pitfall in the standard version of Particle Swarm Optimization (PSO) is that it might get... more A major pitfall in the standard version of Particle Swarm Optimization (PSO) is that it might get stuck in the local optima. In order to escape this issue, a novel hybrid model based on a combination of PSO and Ant-Lion Optimization (ALO) is proposed in this work. The proposed method, called H-PSO-ALO, uses a local search strategy by employing the Ant-Lion algorithm to select the less correlated and salient feature subset. The objective is to improve the prediction accuracy and adaptability of the model in various datasets by balancing the exploration and exploitation processes. The performance of our method has is evaluated on benchmark classification problems, CEC 2017 benchmark problems, and some well-known datasets.in order to verify the performance, four algorithms, including FDR-PSO, CLPSO, HFPSO, and MPSO, are elected to be compared with the efficiency of H-PSO-ALO. Considering the experimental results, the proposed method outperforms the others in many cases, so it seems that it is a desirable candidate for the optimization problems on real-world datasets.

Research paper thumbnail of Intelligent application for Heart disease detection using Hybrid Optimization algorithm

Prediction of heart disease is very important because it is one of the causes of death around the... more Prediction of heart disease is very important because it is one of the causes of death around the world. More- over, heart disease prediction in the early stage plays a main role in the treatment and recovery disease and reduces costs of diagnosis disease and side effects it. Ma- chine learning algorithms are able to identify an effective pattern for diagnosis and treatment of the disease and identify effective factors in the disease. this paper is in- vestigated a new hybrid algorithm of Whale Optimiza- tion and Dragonfly algorithm using a machine learning algorithm. the hybrid algorithm employs a Support Vec- tor Machine algorithm for effective Prediction of heart disease. Proposed method is evaluated by Cleveland standard heart disease dataset. The experimental re- sult indicates that the SVM accuracy of 88.89 % and nine features are selected in this respect.

Research paper thumbnail of An Artificial Predictive Modeling Framework for Automatically Detecting Problematic Use of Internet

International Journal of Computer Applications, 2018

The Internet is one of the most influential new communications technologies that have been affect... more The Internet is one of the most influential new communications technologies that have been affected both social and health aspects of users' lives. Despite many advantages and its positive pointes in communication, the excessive use of Internet make a serious danger that has adverse impacts on overall health. The inability of individuals to control the Internet use has been defined as Internet Addiction (IA). There are a lot of studies on IA over the topics of diagnosis, phenomenology, epidemiology, and treatment based on statistical analysis, but a few research works are conducted by machine learning techniques. So our research focuses on diagnosing and counseling to prevent IA by developing prediction models based on ensemble method with machine learning algorithms and finding the most important risk factors in diagnosing the status of users' IA. Experiment results demonstrate that this hybrid machine learning model by considering students field and location along with items 1, 3, 4, 5, 10, 12, 14, 15, 19, 20 from Internet Addiction Test (IAT) as the most important risk factors can identify the status of users' IA with 99.75% accuracy attains a performance superior to traditional single classifier systems.

Research paper thumbnail of On the facility location problem: One-round weighted Voronoi game

Research paper thumbnail of Prediction of the Survival of Kidney Transplantation with imbalanced Data Using Intelligent Algorithms

Comput. Sci. J. Moldova, 2018

Kidney transplantation is one of the effective post-dialysis treatment methods for patients with ... more Kidney transplantation is one of the effective post-dialysis treatment methods for patients with chronic renal failure in the world. Most medical data are imbalanced and the output of algorithms is inefficient with imbalanced data. The aim of this study is to predict the two-year survival rate of kidney transplant patients and provide a more accurate model. We evaluate the data of renal transplant patients in Afzalipour Medical Education Center 2006-2010, Kerman, Iran. Survival prediction of kidney transplantation with MLP and RBF neural networks with two methods of sampling and investigating the factors affecting the survival of kidney transplant in renal transplant patients is considered by the binary particle optimization algorithm and nearest neighbor algorithm. Accuracy of the results can be increased by using the oversampling method in imbalanced medical data, and radial base network model is a suitable model for predicting the survival of kidney transplant patients.

Research paper thumbnail of A Classification Method for E-mail Spam Using a Hybrid Approach for Feature Selection Optimization

journal of sciences islamic republic of iran, 2020

Spam is an unwanted email that is harmful to communications around the world. Spam leads to a gro... more Spam is an unwanted email that is harmful to communications around the world. Spam leads to a growing problem in a personal email, so it would be essential to detect it. Machine learning is very useful to solve this problem as it shows good results in order to learn all the requisite patterns for classification due to its adaptive existence. Nonetheless, in spam detection, there are a large number of features to attend as they play an essential role in detection efficiency. In this article, we're working on a feature selection method to e-mail spam. This approach is considered a hybrid of optimization algorithms and classifiers in machine learning. Binary Whale Optimization (BWO) and Binary Grey Wolf Optimization (BGWO) algorithms are used for feature selection and K-Nearest Neighbor (KNN) and Fuzzy K-Nearest Neighbor (FKNN) algorithms are applied as the classifiers in this research. The proposed method is tested on the "SPAMBASE" datasets from UCI Machine learning Rep...

Research paper thumbnail of Detection of effective factors on the adult Health Literacy level with a meta-heuristic algorithm

Background and Objective:: Health literacy is a global factor in determining the level of social ... more Background and Objective:: Health literacy is a global factor in determining the level of social literacy of persons in the individual and social health. To improve health in a community, it is essential which measuring and identifying effective factors on the health literacy. The purpose of this study was to identify and determine the factors affecting the level of health literacy using a meta-heuristic algorithm. Materials and Methods: In this paper, a hybrid model has been introduced which benefit of bat optimization algorithm and machine learning algorithms to determine the major factors on health literacy level. In our model, the support vector machine algorithm and K-nearest neighbor are used to classify the data. The data set has been extracted from a descriptive-analytic study that was performed on 2133 samples to measure adults' health in South Khorasan Province in 2016. Results: In this study, the combination of bat optimization algorithm and K-nearest neighbor with 93...

Research paper thumbnail of A System for Diagnosis of Coronary Artery Disease based on Neural Networks and Machine Learning Algorithms

International Journal of Computer Applications, 2018

Today, computer aided systems play an important role in various fields of medical science such as... more Today, computer aided systems play an important role in various fields of medical science such as diagnosis and treatment of diseases; therefore, selected tools should minimize error and maximize the confidence. In this study, considering the importance of cardiovascular disease in the world, the coronary artery disease is diagnosed by neural networks and machine learning algorithms. The proposed system employs three types of artificial neural networks, decision tree and Adaboost algorithm to distinguish people who suffer from heart disease and the healthy individuals using Cleveland's dataset. Among these algorithms, the multilayer perceptron neural network has the best performance and is able to predict coronary artery disease with the accuracy, sensitivity and specificity of 94.53%, 86.77%, and 99.39%, respectively. The superiority of the proposed system is obvious comparing to other existing studies because it diagnoses the disease with higher accuracy, sensitivity and more reliability.

Research paper thumbnail of The Application of an Evolutionary Model using Fuzzy Logic on Health Literacy Data

Health Education and Health Promotion, 2019

Analyzing diabetes datasets using data ... [9] Data-mining technologies for diabetes: A systemati... more Analyzing diabetes datasets using data ... [9] Data-mining technologies for diabetes: A systematic ... [10] Systematic review of data mining applications in patient-centered mobile-based information ... [11] Privacy preserving distributed association rule mining approach on vertically partitioned healthcare ... [12] Prediction of benign and malignant breast cancer using data mining ... [13] Application of data mining: Diabetes health care in young and ... [14] Breast cancer diagnosis via data mining: performance analysis of seven different ... [15] Data mining techniques and applications-a decade review from 2000 to ... [16] Data mining and medical world: Breast cancers' diagnosis, treatment, prognosis and ... [17] Data mining application for exploring the relationship between addiction and ... [18] Data mining algorithms and techniques in mental health: A systematic ... [19] Applying data mining techniques in ... [20] Particle swarm optimization: A survey of historical and recent developments with hybridization ... [21] A comprehensive survey on particle swarm optimization algorithm and its ... [22] Particle swarm ... [23] Compressed kNN: K-nearest neighbors with data ... [24] Application of the weighted k-nearest neighbor algorithm for short-term load ... [25] Fuzzy k-nearest neighbor method to classify data in a closed ... [26] Hybrid intelligent system for cardiac arrhythmia classification with fuzzy k-nearest neighbors and neural networks combined with a fuzzy ... [27] Health literacy status and understanding of the prescription instructions in diabetic ... [28] A new adaptive testing algorithm for shortening health literacy ... Aims Health literacy (HL) is the main factor shows health literate level of people in a certain society. Discovering and understanding affective factors on HL level could lead experts to improve these factors in the target community. This study aimed to Health Literacy classification of population and find a major component with data mining approaches. Instruments and Methods In this paper, we have acquired more details about major factors on the health literacy level of target society by assessing evolutionary methods. We benefit of Particle Swarm Optimization (PSO) and KNN and fuzzy KNN algorithm for classification and use wrapper technique for feature selection by our model. Feature selection are done as weighted features and selects the most effective features of health literacy. Our proposed model evaluates a data set of Health Literacy by two classifiers with/without fuzzy logic. Applied data set is a real data gathered from a descriptive-analytic cross-sectional study on adult population include 2133 record with 74 attributes in 2016 at South Khorasan province. We have gained effective factors on HL level of the population according to regions and total population without using any statistical analysis tools with the lowest human interference by an evolutionary method. Findings Proposed model have found effective factors on the health literacy level of population in South Khorasan province. Results are obtained 92.02% accuracy for the total population and 97.99% for regions population. Conclusion Simulations demonstrate the evolutionary method is a suitable way for extracting results from health data sets and also shows the superiority of the proposed method.

Research paper thumbnail of Intelligent application for Heart disease detection using Hybrid Optimization algorithm

International Symposium on Algorithms and Computation, Jun 1, 2019

Prediction of heart disease is very important because it is one of the causes of death around the... more Prediction of heart disease is very important because it is one of the causes of death around the world. Moreover, heart disease prediction in the early stage plays a main role in the treatment and recovery disease and reduces costs of diagnosis disease and side effects it. Machine learning algorithms are able to identify an effective pattern for diagnosis and treatment of the disease and identify effective factors in the disease. this paper is investigated a new hybrid algorithm of Whale Optimization and Dragonfly algorithm using a machine learning algorithm. the hybrid algorithm employs a Support Vector Machine algorithm for effective Prediction of heart disease. Proposed method is evaluated by Cleveland standard heart disease dataset. The experimental result indicates that the SVM accuracy of 88.89 % and nine features are selected in this respect.

Research paper thumbnail of Prediction and determining the effective factors on the survival transplanted kidney for five-year in imbalanced data by the meta-heuristic approach and machine learning

پردازش علائم و دادهها, Mar 1, 2019

Research paper thumbnail of The Application of an Evolutionary Model using Fuzzy Logic on Health Literacy Data

Health education & health promotion, Jul 1, 2019

Analyzing diabetes datasets using data ... [9] Data-mining technologies for diabetes: A systemati... more Analyzing diabetes datasets using data ... [9] Data-mining technologies for diabetes: A systematic ... [10] Systematic review of data mining applications in patient-centered mobile-based information ... [11] Privacy preserving distributed association rule mining approach on vertically partitioned healthcare ... [12] Prediction of benign and malignant breast cancer using data mining ... [13] Application of data mining: Diabetes health care in young and ... [14] Breast cancer diagnosis via data mining: performance analysis of seven different ... [15] Data mining techniques and applications-a decade review from 2000 to ... [16] Data mining and medical world: Breast cancers' diagnosis, treatment, prognosis and ... [17] Data mining application for exploring the relationship between addiction and ... [18] Data mining algorithms and techniques in mental health: A systematic ... [19] Applying data mining techniques in ... [20] Particle swarm optimization: A survey of historical and recent developments with hybridization ... [21] A comprehensive survey on particle swarm optimization algorithm and its ... [22] Particle swarm ... [23] Compressed kNN: K-nearest neighbors with data ... [24] Application of the weighted k-nearest neighbor algorithm for short-term load ... [25] Fuzzy k-nearest neighbor method to classify data in a closed ... [26] Hybrid intelligent system for cardiac arrhythmia classification with fuzzy k-nearest neighbors and neural networks combined with a fuzzy ... [27] Health literacy status and understanding of the prescription instructions in diabetic ... [28] A new adaptive testing algorithm for shortening health literacy ... Aims Health literacy (HL) is the main factor shows health literate level of people in a certain society. Discovering and understanding affective factors on HL level could lead experts to improve these factors in the target community. This study aimed to Health Literacy classification of population and find a major component with data mining approaches. Instruments and Methods In this paper, we have acquired more details about major factors on the health literacy level of target society by assessing evolutionary methods. We benefit of Particle Swarm Optimization (PSO) and KNN and fuzzy KNN algorithm for classification and use wrapper technique for feature selection by our model. Feature selection are done as weighted features and selects the most effective features of health literacy. Our proposed model evaluates a data set of Health Literacy by two classifiers with/without fuzzy logic. Applied data set is a real data gathered from a descriptive-analytic cross-sectional study on adult population include 2133 record with 74 attributes in 2016 at South Khorasan province. We have gained effective factors on HL level of the population according to regions and total population without using any statistical analysis tools with the lowest human interference by an evolutionary method. Findings Proposed model have found effective factors on the health literacy level of population in South Khorasan province. Results are obtained 92.02% accuracy for the total population and 97.99% for regions population. Conclusion Simulations demonstrate the evolutionary method is a suitable way for extracting results from health data sets and also shows the superiority of the proposed method.

Research paper thumbnail of An Artificial Predictive Modeling Framework for Automatically Detecting Problematic Use of Internet

International journal of computer applications, May 17, 2018

The Internet is one of the most influential new communications technologies that have been affect... more The Internet is one of the most influential new communications technologies that have been affected both social and health aspects of users' lives. Despite many advantages and its positive pointes in communication, the excessive use of Internet make a serious danger that has adverse impacts on overall health. The inability of individuals to control the Internet use has been defined as Internet Addiction (IA). There are a lot of studies on IA over the topics of diagnosis, phenomenology, epidemiology, and treatment based on statistical analysis, but a few research works are conducted by machine learning techniques. So our research focuses on diagnosing and counseling to prevent IA by developing prediction models based on ensemble method with machine learning algorithms and finding the most important risk factors in diagnosing the status of users' IA. Experiment results demonstrate that this hybrid machine learning model by considering students field and location along with items 1, 3, 4, 5, 10, 12, 14, 15, 19, 20 from Internet Addiction Test (IAT) as the most important risk factors can identify the status of users' IA with 99.75% accuracy attains a performance superior to traditional single classifier systems.

Research paper thumbnail of On the facility location problem: One-round weighted Voronoi game

Social Science Research Network, 2020

Research paper thumbnail of H-BwoaSvm: A Hybrid Model for Classification and Feature Selection of Mammography Screening Behavior Data

Journal of AI and Data Mining, Apr 1, 2020

Breast cancer is one of the most common cancer in the world. An early detection of cancers causes... more Breast cancer is one of the most common cancer in the world. An early detection of cancers causes a significant reduction in the morbidity rate and treatment costs. Mammography is a known effective diagnosis method of breast cancer. A way for mammography screening behavior identification is women's awareness evaluation for participating in the mammography screening programs. Today, intelligence systems could identify the main factors involved in a specific incident. These could help the experts a wide range of areas, specially health scopes such as prevention, diagnosis, and treatment. In this paper, we use a hybrid model called H-BwoaSvm BWOA is used for detecting the effective factors involved in the mammography screening behavior and SVM for classification. Our model is applied on a data-set which is collected from a segmental analytical descriptive study on 2256 women. The proposed model is operated on a data-set with 82.27% and 98.89% accuracy and selects the effective features on the mammography screening behavior.

Research paper thumbnail of Credit Risk Assessment Using Learning Algorithms for Feature Selection

Fuzzy Information and Engineering, Oct 1, 2020

Firefly algorithm is one of the latest outstanding bio-inspired algorithms, which could be manipu... more Firefly algorithm is one of the latest outstanding bio-inspired algorithms, which could be manipulated in solving continuous or discrete optimisation problems. In this context, we have utilised the firefly algorithm accompanied by five well-known models of feature selection classifiers to have an accurate estimation of risk, and further to improve the interpret-ability of credit card prediction. One of the significant challenges in the real-world datasets is how to select features. As most of the datasets are unbalanced, the selection of features turns to the maximum class of data that is not fair. To overcome this issue, we have balanced the data using the SMOTE method. Our experimental results on four datasets show that balancing data has increased accuracy. In addition, using a hybrid firefly algorithm, the optimal combination of features that predicts the target class label is achieved. The selected features by the proposed method besides been reduced can represent both majority and minority classes.

Research paper thumbnail of A System for Diagnosis of Coronary Artery Disease based on Neural Networks and Machine Learning Algorithms

International journal of computer applications, Sep 17, 2018

Today, computer aided systems play an important role in various fields of medical science such as... more Today, computer aided systems play an important role in various fields of medical science such as diagnosis and treatment of diseases; therefore, selected tools should minimize error and maximize the confidence. In this study, considering the importance of cardiovascular disease in the world, the coronary artery disease is diagnosed by neural networks and machine learning algorithms. The proposed system employs three types of artificial neural networks, decision tree and Adaboost algorithm to distinguish people who suffer from heart disease and the healthy individuals using Cleveland's dataset. Among these algorithms, the multilayer perceptron neural network has the best performance and is able to predict coronary artery disease with the accuracy, sensitivity and specificity of 94.53%, 86.77%, and 99.39%, respectively. The superiority of the proposed system is obvious comparing to other existing studies because it diagnoses the disease with higher accuracy, sensitivity and more reliability.

Research paper thumbnail of Prediction of the Survival of Kidney Transplantation with imbalanced Data Using Intelligent Algorithms

DOAJ (DOAJ: Directory of Open Access Journals), Aug 1, 2018

Kidney transplantation is one of the effective post-dialysis treatment methods for patients with ... more Kidney transplantation is one of the effective post-dialysis treatment methods for patients with chronic renal failure in the world. Most medical data are imbalanced and the output of algorithms is inefficient with imbalanced data. The aim of this study is to predict the two-year survival rate of kidney transplant patients and provide a more accurate model. We evaluate the data of renal transplant patients in Afzalipour Medical Education Center 2006-2010, Kerman, Iran. Survival prediction of kidney transplantation with MLP and RBF neural networks with two methods of sampling and investigating the factors affecting the survival of kidney transplant in renal transplant patients is considered by the binary particle optimization algorithm and nearest neighbor algorithm. Accuracy of the results can be increased by using the oversampling method in imbalanced medical data, and radial base network model is a suitable model for predicting the survival of kidney transplant patients.

Research paper thumbnail of Hybrid Algorithms of Whale optimization algorithm and k-nearest neighbor to Predict the liver disease

EAI endorsed transactions on context-aware systems and applications, May 23, 2019

Liver Disease is one of the most common diseases which can be prevented by early diagnosis and up... more Liver Disease is one of the most common diseases which can be prevented by early diagnosis and up-todate treatment. Advances in machine learning and intelligence techniques have led to the effective diagnosis and prediction of diseases to improve the treatment of patients and reduce the cost of treatment. Whale Optimization Algorithm is a swarm intelligent technique, inspired by the social behavior of whales. One of the effective classification algorithms is K-Nearest Neighbor which is employed for pattern recognition. This paper was designed to investigate the prediction of Liver Disease using a hybrid algorithm including KNN and WOA. In order to evaluate the efficiency of hybrid algorithm, two datasets of liver disease including BUPA and ILPD were used. The results showed that 81.24% and 91.28% of accuracy was gained by the proposed algorithm for BUPA and ILPD, respectively. Experimental results showed that the hybrid WON-KNN is a better classifier to predict the liver diseases

Research paper thumbnail of Credit Risk Assessment Using Learning Algorithms for Feature Selection

Fuzzy Information and Engineering, 2020

Firefly algorithm is one of the latest outstanding bio-inspired algorithms, which could be manipu... more Firefly algorithm is one of the latest outstanding bio-inspired algorithms, which could be manipulated in solving continuous or discrete optimisation problems. In this context, we have utilised the firefly algorithm accompanied by five well-known models of feature selection classifiers to have an accurate estimation of risk, and further to improve the interpret-ability of credit card prediction. One of the significant challenges in the real-world datasets is how to select features. As most of the datasets are unbalanced, the selection of features turns to the maximum class of data that is not fair. To overcome this issue, we have balanced the data using the SMOTE method. Our experimental results on four datasets show that balancing data has increased accuracy. In addition, using a hybrid firefly algorithm, the optimal combination of features that predicts the target class label is achieved. The selected features by the proposed method besides been reduced can represent both majority and minority classes.

Research paper thumbnail of Hybrid Particle Swarm Optimization with Ant-Lion Optimization: Experimental in Benchmarks and Applications

Journal of AI and Data Mining, Nov 6, 2021

A major pitfall in the standard version of Particle Swarm Optimization (PSO) is that it might get... more A major pitfall in the standard version of Particle Swarm Optimization (PSO) is that it might get stuck in the local optima. In order to escape this issue, a novel hybrid model based on a combination of PSO and Ant-Lion Optimization (ALO) is proposed in this work. The proposed method, called H-PSO-ALO, uses a local search strategy by employing the Ant-Lion algorithm to select the less correlated and salient feature subset. The objective is to improve the prediction accuracy and adaptability of the model in various datasets by balancing the exploration and exploitation processes. The performance of our method has is evaluated on benchmark classification problems, CEC 2017 benchmark problems, and some well-known datasets.in order to verify the performance, four algorithms, including FDR-PSO, CLPSO, HFPSO, and MPSO, are elected to be compared with the efficiency of H-PSO-ALO. Considering the experimental results, the proposed method outperforms the others in many cases, so it seems that it is a desirable candidate for the optimization problems on real-world datasets.

Research paper thumbnail of Intelligent application for Heart disease detection using Hybrid Optimization algorithm

Prediction of heart disease is very important because it is one of the causes of death around the... more Prediction of heart disease is very important because it is one of the causes of death around the world. More- over, heart disease prediction in the early stage plays a main role in the treatment and recovery disease and reduces costs of diagnosis disease and side effects it. Ma- chine learning algorithms are able to identify an effective pattern for diagnosis and treatment of the disease and identify effective factors in the disease. this paper is in- vestigated a new hybrid algorithm of Whale Optimiza- tion and Dragonfly algorithm using a machine learning algorithm. the hybrid algorithm employs a Support Vec- tor Machine algorithm for effective Prediction of heart disease. Proposed method is evaluated by Cleveland standard heart disease dataset. The experimental re- sult indicates that the SVM accuracy of 88.89 % and nine features are selected in this respect.

Research paper thumbnail of An Artificial Predictive Modeling Framework for Automatically Detecting Problematic Use of Internet

International Journal of Computer Applications, 2018

The Internet is one of the most influential new communications technologies that have been affect... more The Internet is one of the most influential new communications technologies that have been affected both social and health aspects of users' lives. Despite many advantages and its positive pointes in communication, the excessive use of Internet make a serious danger that has adverse impacts on overall health. The inability of individuals to control the Internet use has been defined as Internet Addiction (IA). There are a lot of studies on IA over the topics of diagnosis, phenomenology, epidemiology, and treatment based on statistical analysis, but a few research works are conducted by machine learning techniques. So our research focuses on diagnosing and counseling to prevent IA by developing prediction models based on ensemble method with machine learning algorithms and finding the most important risk factors in diagnosing the status of users' IA. Experiment results demonstrate that this hybrid machine learning model by considering students field and location along with items 1, 3, 4, 5, 10, 12, 14, 15, 19, 20 from Internet Addiction Test (IAT) as the most important risk factors can identify the status of users' IA with 99.75% accuracy attains a performance superior to traditional single classifier systems.

Research paper thumbnail of On the facility location problem: One-round weighted Voronoi game

Research paper thumbnail of Prediction of the Survival of Kidney Transplantation with imbalanced Data Using Intelligent Algorithms

Comput. Sci. J. Moldova, 2018

Kidney transplantation is one of the effective post-dialysis treatment methods for patients with ... more Kidney transplantation is one of the effective post-dialysis treatment methods for patients with chronic renal failure in the world. Most medical data are imbalanced and the output of algorithms is inefficient with imbalanced data. The aim of this study is to predict the two-year survival rate of kidney transplant patients and provide a more accurate model. We evaluate the data of renal transplant patients in Afzalipour Medical Education Center 2006-2010, Kerman, Iran. Survival prediction of kidney transplantation with MLP and RBF neural networks with two methods of sampling and investigating the factors affecting the survival of kidney transplant in renal transplant patients is considered by the binary particle optimization algorithm and nearest neighbor algorithm. Accuracy of the results can be increased by using the oversampling method in imbalanced medical data, and radial base network model is a suitable model for predicting the survival of kidney transplant patients.

Research paper thumbnail of A Classification Method for E-mail Spam Using a Hybrid Approach for Feature Selection Optimization

journal of sciences islamic republic of iran, 2020

Spam is an unwanted email that is harmful to communications around the world. Spam leads to a gro... more Spam is an unwanted email that is harmful to communications around the world. Spam leads to a growing problem in a personal email, so it would be essential to detect it. Machine learning is very useful to solve this problem as it shows good results in order to learn all the requisite patterns for classification due to its adaptive existence. Nonetheless, in spam detection, there are a large number of features to attend as they play an essential role in detection efficiency. In this article, we're working on a feature selection method to e-mail spam. This approach is considered a hybrid of optimization algorithms and classifiers in machine learning. Binary Whale Optimization (BWO) and Binary Grey Wolf Optimization (BGWO) algorithms are used for feature selection and K-Nearest Neighbor (KNN) and Fuzzy K-Nearest Neighbor (FKNN) algorithms are applied as the classifiers in this research. The proposed method is tested on the "SPAMBASE" datasets from UCI Machine learning Rep...

Research paper thumbnail of Detection of effective factors on the adult Health Literacy level with a meta-heuristic algorithm

Background and Objective:: Health literacy is a global factor in determining the level of social ... more Background and Objective:: Health literacy is a global factor in determining the level of social literacy of persons in the individual and social health. To improve health in a community, it is essential which measuring and identifying effective factors on the health literacy. The purpose of this study was to identify and determine the factors affecting the level of health literacy using a meta-heuristic algorithm. Materials and Methods: In this paper, a hybrid model has been introduced which benefit of bat optimization algorithm and machine learning algorithms to determine the major factors on health literacy level. In our model, the support vector machine algorithm and K-nearest neighbor are used to classify the data. The data set has been extracted from a descriptive-analytic study that was performed on 2133 samples to measure adults' health in South Khorasan Province in 2016. Results: In this study, the combination of bat optimization algorithm and K-nearest neighbor with 93...

Research paper thumbnail of A System for Diagnosis of Coronary Artery Disease based on Neural Networks and Machine Learning Algorithms

International Journal of Computer Applications, 2018

Today, computer aided systems play an important role in various fields of medical science such as... more Today, computer aided systems play an important role in various fields of medical science such as diagnosis and treatment of diseases; therefore, selected tools should minimize error and maximize the confidence. In this study, considering the importance of cardiovascular disease in the world, the coronary artery disease is diagnosed by neural networks and machine learning algorithms. The proposed system employs three types of artificial neural networks, decision tree and Adaboost algorithm to distinguish people who suffer from heart disease and the healthy individuals using Cleveland's dataset. Among these algorithms, the multilayer perceptron neural network has the best performance and is able to predict coronary artery disease with the accuracy, sensitivity and specificity of 94.53%, 86.77%, and 99.39%, respectively. The superiority of the proposed system is obvious comparing to other existing studies because it diagnoses the disease with higher accuracy, sensitivity and more reliability.

Research paper thumbnail of The Application of an Evolutionary Model using Fuzzy Logic on Health Literacy Data

Health Education and Health Promotion, 2019

Analyzing diabetes datasets using data ... [9] Data-mining technologies for diabetes: A systemati... more Analyzing diabetes datasets using data ... [9] Data-mining technologies for diabetes: A systematic ... [10] Systematic review of data mining applications in patient-centered mobile-based information ... [11] Privacy preserving distributed association rule mining approach on vertically partitioned healthcare ... [12] Prediction of benign and malignant breast cancer using data mining ... [13] Application of data mining: Diabetes health care in young and ... [14] Breast cancer diagnosis via data mining: performance analysis of seven different ... [15] Data mining techniques and applications-a decade review from 2000 to ... [16] Data mining and medical world: Breast cancers' diagnosis, treatment, prognosis and ... [17] Data mining application for exploring the relationship between addiction and ... [18] Data mining algorithms and techniques in mental health: A systematic ... [19] Applying data mining techniques in ... [20] Particle swarm optimization: A survey of historical and recent developments with hybridization ... [21] A comprehensive survey on particle swarm optimization algorithm and its ... [22] Particle swarm ... [23] Compressed kNN: K-nearest neighbors with data ... [24] Application of the weighted k-nearest neighbor algorithm for short-term load ... [25] Fuzzy k-nearest neighbor method to classify data in a closed ... [26] Hybrid intelligent system for cardiac arrhythmia classification with fuzzy k-nearest neighbors and neural networks combined with a fuzzy ... [27] Health literacy status and understanding of the prescription instructions in diabetic ... [28] A new adaptive testing algorithm for shortening health literacy ... Aims Health literacy (HL) is the main factor shows health literate level of people in a certain society. Discovering and understanding affective factors on HL level could lead experts to improve these factors in the target community. This study aimed to Health Literacy classification of population and find a major component with data mining approaches. Instruments and Methods In this paper, we have acquired more details about major factors on the health literacy level of target society by assessing evolutionary methods. We benefit of Particle Swarm Optimization (PSO) and KNN and fuzzy KNN algorithm for classification and use wrapper technique for feature selection by our model. Feature selection are done as weighted features and selects the most effective features of health literacy. Our proposed model evaluates a data set of Health Literacy by two classifiers with/without fuzzy logic. Applied data set is a real data gathered from a descriptive-analytic cross-sectional study on adult population include 2133 record with 74 attributes in 2016 at South Khorasan province. We have gained effective factors on HL level of the population according to regions and total population without using any statistical analysis tools with the lowest human interference by an evolutionary method. Findings Proposed model have found effective factors on the health literacy level of population in South Khorasan province. Results are obtained 92.02% accuracy for the total population and 97.99% for regions population. Conclusion Simulations demonstrate the evolutionary method is a suitable way for extracting results from health data sets and also shows the superiority of the proposed method.