Hassan Rezaei - Academia.edu (original) (raw)

Papers by Hassan Rezaei

Research paper thumbnail of Internal validation and comparison of predictive models to determine success rate of infertility treatments: a retrospective study of 2485 cycles

Scientific Reports

Infertility is a significant health problem and assisted reproductive technologies to treat infer... more Infertility is a significant health problem and assisted reproductive technologies to treat infertility. Despite all efforts, the success rate of these methods is still low. Also, each of these methods has side effects and costs. Therefore, accurate prediction of treatment success rate is a clinical challenge. This retrospective study aimed to internally validate and compare various machine learning models for predicting the clinical pregnancy rate (CPR) of infertility treatment. For this purpose, data from 1931 patients consisting of in vitro fertilization (IVF) or intra cytoplasmic sperm injection (ICSI) (733) and intra uterine insemination (IUI) (1196) treatments were included. Also, no egg or sperm donation data were used. The performance of machine learning algorithms to predict clinical pregnancy were expressed in terms of accuracy, recall, F-score, positive predictive value (PPV), brier score (BS), Matthew correlation coefficient (MCC), and receiver operating characteristic. ...

Research paper thumbnail of ABC_M: a hybrid algorithm ABC and BA

International Journal of Control and Automation, 2016

Optimization is ability of find the best solution in the existing situations. Optimization is use... more Optimization is ability of find the best solution in the existing situations. Optimization is used in design and maintenance of systems engineering, economic, social and even necessary to reduce costs and increase profits. The widespread importance of optimization problem has a lot of grown. There are many algorithms for optimization and they are trying to reduce the disadvantages of other methods and increase the ability of resolve the problem. This paper proposed an adaptive ABC and Bat algorithm. The idea of algorithm is improved speed of convergence and optimized search in search space for ABC algorithm with Bat algorithm. The proposed algorithm is compared with ABC and Bat algorithm on benchmark function and test shows ABC_M are improved obviously. Also can be known a complete local search is more important from global search.

Research paper thumbnail of Results on ips Hypergroups

Research paper thumbnail of A New Similarity Measures of Intuitionistic Fuzzy Sets and Application to Pattern Recognitions

Advanced Materials Research, 2011

Intuitionistic fuzzy sets (IFSs), proposed by Atanassov, have gained attention from researchers f... more Intuitionistic fuzzy sets (IFSs), proposed by Atanassov, have gained attention from researchers for their applications in various fields. Then similarity measures between IFSs were developed. In this paper, firstly, some existing measures of similarity are reviewed. Then a new similarity measure is proposed and the relationships between some similarity measures are proved. Finally, the similarity measures of IFSs is applied to pattern recognition and the proposed similarity measures can provide a useful way for measuring IFSs more effectively.

Research paper thumbnail of Some Classifications of Hyperk-Algebras of Order 3

In this paper rst we give some de nitions and examples on hyperKalgebras. Then we give some theor... more In this paper rst we give some de nitions and examples on hyperKalgebras. Then we give some theorems and obtain some results which are needed to state and prove the main theorems of this manuscript (Theorems 3.16 and 3.21). In these theorems we give some classi cations of hyperK-algebras of order 3 which satisfy the normal condition or simple condition. Finally we give two open problems.

Research paper thumbnail of Partial similarity measure of uncertain random variables and its application to portfolio selection

Journal of Intelligent & Fuzzy Systems, 2020

In this paper, we introduce a collaborative and modern annotation tool for audio and speech: audi... more In this paper, we introduce a collaborative and modern annotation tool for audio and speech: audino. The tool allows annotators to define and describe temporal segmentation in audios. These segments can be labelled and transcribed easily using a dynamically generated form. An admin can centrally control user roles and project assignment through the admin dashboard. The dashboard also enables describing labels and their values. The annotations can easily be exported in JSON format for further analysis. The tool allows audio data and their corresponding annotations to be uploaded and assigned to a user through a key-based API. The flexibility available in the annotation tool enables annotation for Speech Scoring, Voice Activity Detection (VAD), Speaker Diarisation, Speaker Identification, Speech Recognition, Emotion Recognition tasks and more. The MIT open source license allows it to be used for academic and commercial projects. CCS CONCEPTS • Applied computing → Annotation.

Research paper thumbnail of New distance and similarity measures for hesitant fuzzy sets and their application in hierarchical clustering

Journal of Intelligent & Fuzzy Systems, 2020

The hesitant fuzzy sets (HFSs) are an extension of the classical fuzzy sets. The membership degre... more The hesitant fuzzy sets (HFSs) are an extension of the classical fuzzy sets. The membership degree of each element in a hesitant fuzzy set can be a set of possible values in the interval [0,1]. On the other hand, distance and similarity measures are important tools in several applications such as pattern recognition, clustering, medical diagnosis, etc. Hence, numerous studies have focused on investigating distance and similarity measures for HFSs. In this paper, some improved distance and similarity measures are introduced for the HFSs, considering the variation range as a hesitance degree for these sets. Comparing the proposed measures to some available distance and similarity measures indicated the better results of the proposed measures. Finally, the application of the proposed measures was investigated in the clustering.

Research paper thumbnail of HFSMOOK-Means: An Improved K-Means Algorithm Using Hesitant Fuzzy Sets and Multi-objective Optimization

Arabian Journal for Science and Engineering, 2020

Clustering is considered as one of the important methods in data mining. The performance of the K... more Clustering is considered as one of the important methods in data mining. The performance of the K-means algorithm, as one of the most common clustering methods, is high sensitivity to the initial cluster centers. Hence, selecting appropriate initial cluster centers for implementing the algorithm improves clustering resulted from the algorithm. The present study aims to find suitable initial cluster centers for the K-means. In fact, the initial cluster centers should be selected in such a way that clusters with high separation and high density can be obtained. Therefore, in this paper, finding initial cluster centers is considered as a multi-objective optimization problem through maximizing the distance between the initial cluster centers, as well as the neighbor density of the initial cluster centers. Solving the above problem through using the MOPSO algorithm provided a set of initial cluster centers of the candidate. Then, the hesitant fuzzy sets were used to evaluate the clusters generated from initial cluster centers by considering separation, cohesion and silhouette index. After that, the concept of informational energy of hesitant fuzzy sets is used, by which non-dominated particles in the Pareto optimal set were ranked and the initial cluster centers were selected for starting the K-means algorithm. The proposed HFSMOOK-means method was compared with several clustering algorithms by considering common and widely used criteria. The results indicated the successful performance of HFSMOOK-means in the majority of the datasets compared to the other algorithms.

Research paper thumbnail of Some results on canonical, cyclic hypergroups and join spaces

In this note, all join spaces associated to fuzzy subsets of a set with three elements, all canon... more In this note, all join spaces associated to fuzzy subsets of a set with three elements, all canonical hypergroups of order 3, spherical join space of order 3 and are characterized.

Research paper thumbnail of New method for rapid diagnosis of Hepatitis disease based on reduction feature and machine learning

Journal of Advanced Computer Science & Technology, 2015

Hepatitis disease is caused by liver injury. Rapid diagnosis of this disease prevents its develop... more Hepatitis disease is caused by liver injury. Rapid diagnosis of this disease prevents its development and suffering to cirrhosis of the liver. Data mining is a new branch of science that helps physicians for proper decision making. In data mining using reduction feature and machine learning algorithms are useful for reducing the complexity of the problem and method of disease diagnosis, respectively. In this study, a new algorithm is proposed for hepatitis diagnosis according to Principal Component Analysis (PCA) and Error Minimized Extreme Learning Machine (EMELM). The algorithm includes two stages; in reduction feature phase, missing records were deleted and hepatitis dataset was normalized in [0,1] range. Thereafter, analysis of the principal component was applied for reduction feature. In classification phase, the reduced dataset is classified using EMELM. For evaluation of the algorithm, hepatitis disease dataset from UCI Machine Learning Repository (University of California) w...

Research paper thumbnail of Problem solving of container loading using genetic algorithm based on modified random keys

Journal of Advanced Computer Science & Technology, 2015

This article presents a solution to the container loading problem. Container loading problem deal... more This article presents a solution to the container loading problem. Container loading problem deals with how to put the cube boxes with different sizes in a container. Our proposed method is based on a particular kind of genetic algorithm based on biased random keys. In the proposed algorithm, we will face generations' extinction. Population decreases with time and with the staircase changes in the rate of elitism, the algorithm is guided towards the global optimum. Biased random keys in the proposed method are provided as discrete. The algorithm also provides the chromosomes that store more than one ability. In order to solve container loading using a placement strategy, due to the size of the boxes and containers, the containers are classified as small units and equal unites in size. Finally the algorithm presented in this paper was compared with three other methods that are based on evolutionary algorithms. The results show that the proposed algorithm has better performance in terms of results and performance time in relation to other methods.

Research paper thumbnail of Classifications of hyper BCK-algebras of order 3

ABSTRACT In this paper we first review the notion of a hyper BCK-algebra, which is a generalizati... more ABSTRACT In this paper we first review the notion of a hyper BCK-algebra, which is a generalization of a BCK-algebra, and we also give some properties of this notion. Then we give the concepts of (strong) hyper BCK-ideals and hyper BCK-algebras, which satisfy the simple or normal conditions. After that, by considering the notion of an isomorphism between two hyper BCK-algebras, we distinguish all hyper BCK-algebras of order 3 which satisfy either the simple condition or the normal condition. In fact there are 19 hyper BCK-algebras of order 3 up to isomorphism.

Research paper thumbnail of The Scrutiny of Variation in the Number of Fuzzy Rules and Membership Functions in a New Genetic-Fuzzy System in Approximation and Prediction Problems

International Journal of Information and Electronics Engineering, 2013

This paper shows a new fuzzy system was improved using genetic algorithm to handle fuzzy inferenc... more This paper shows a new fuzzy system was improved using genetic algorithm to handle fuzzy inference system as a function approximator and time series predictor. The system was developed generality that trained with genetic algorithms (GAs) corresponding to special problem and would be evaluated with different number of rules and membership functions. Then, compare the efficacy of variation of these two parameters in behavior of the system and show the method that achieves an efficient structure in both of them. Also, the proposed GA-Fuzzy inference system successfully predicts a benchmark problem and approximates an introduced function and results have been shown.

Research paper thumbnail of New Similarity Measure Between Two Fuzzy Sets

Journal of Advanced Computational Intelligence and Intelligent Informatics, 2006

We propose a new similarity measure between two fuzzy sets based on their relative sigma count an... more We propose a new similarity measure between two fuzzy sets based on their relative sigma count and extend it to define two other measures, one a similarity measure between elements in fuzzy sets and the second a similarity measure between fuzzy sets in which all elements in the universe of discourse are weighted. We compare our proposal to several previous measures proposed in [1-6].

Research paper thumbnail of Internal validation and comparison of predictive models to determine success rate of infertility treatments: a retrospective study of 2485 cycles

Scientific Reports

Infertility is a significant health problem and assisted reproductive technologies to treat infer... more Infertility is a significant health problem and assisted reproductive technologies to treat infertility. Despite all efforts, the success rate of these methods is still low. Also, each of these methods has side effects and costs. Therefore, accurate prediction of treatment success rate is a clinical challenge. This retrospective study aimed to internally validate and compare various machine learning models for predicting the clinical pregnancy rate (CPR) of infertility treatment. For this purpose, data from 1931 patients consisting of in vitro fertilization (IVF) or intra cytoplasmic sperm injection (ICSI) (733) and intra uterine insemination (IUI) (1196) treatments were included. Also, no egg or sperm donation data were used. The performance of machine learning algorithms to predict clinical pregnancy were expressed in terms of accuracy, recall, F-score, positive predictive value (PPV), brier score (BS), Matthew correlation coefficient (MCC), and receiver operating characteristic. ...

Research paper thumbnail of ABC_M: a hybrid algorithm ABC and BA

International Journal of Control and Automation, 2016

Optimization is ability of find the best solution in the existing situations. Optimization is use... more Optimization is ability of find the best solution in the existing situations. Optimization is used in design and maintenance of systems engineering, economic, social and even necessary to reduce costs and increase profits. The widespread importance of optimization problem has a lot of grown. There are many algorithms for optimization and they are trying to reduce the disadvantages of other methods and increase the ability of resolve the problem. This paper proposed an adaptive ABC and Bat algorithm. The idea of algorithm is improved speed of convergence and optimized search in search space for ABC algorithm with Bat algorithm. The proposed algorithm is compared with ABC and Bat algorithm on benchmark function and test shows ABC_M are improved obviously. Also can be known a complete local search is more important from global search.

Research paper thumbnail of Results on ips Hypergroups

Research paper thumbnail of A New Similarity Measures of Intuitionistic Fuzzy Sets and Application to Pattern Recognitions

Advanced Materials Research, 2011

Intuitionistic fuzzy sets (IFSs), proposed by Atanassov, have gained attention from researchers f... more Intuitionistic fuzzy sets (IFSs), proposed by Atanassov, have gained attention from researchers for their applications in various fields. Then similarity measures between IFSs were developed. In this paper, firstly, some existing measures of similarity are reviewed. Then a new similarity measure is proposed and the relationships between some similarity measures are proved. Finally, the similarity measures of IFSs is applied to pattern recognition and the proposed similarity measures can provide a useful way for measuring IFSs more effectively.

Research paper thumbnail of Some Classifications of Hyperk-Algebras of Order 3

In this paper rst we give some de nitions and examples on hyperKalgebras. Then we give some theor... more In this paper rst we give some de nitions and examples on hyperKalgebras. Then we give some theorems and obtain some results which are needed to state and prove the main theorems of this manuscript (Theorems 3.16 and 3.21). In these theorems we give some classi cations of hyperK-algebras of order 3 which satisfy the normal condition or simple condition. Finally we give two open problems.

Research paper thumbnail of Partial similarity measure of uncertain random variables and its application to portfolio selection

Journal of Intelligent & Fuzzy Systems, 2020

In this paper, we introduce a collaborative and modern annotation tool for audio and speech: audi... more In this paper, we introduce a collaborative and modern annotation tool for audio and speech: audino. The tool allows annotators to define and describe temporal segmentation in audios. These segments can be labelled and transcribed easily using a dynamically generated form. An admin can centrally control user roles and project assignment through the admin dashboard. The dashboard also enables describing labels and their values. The annotations can easily be exported in JSON format for further analysis. The tool allows audio data and their corresponding annotations to be uploaded and assigned to a user through a key-based API. The flexibility available in the annotation tool enables annotation for Speech Scoring, Voice Activity Detection (VAD), Speaker Diarisation, Speaker Identification, Speech Recognition, Emotion Recognition tasks and more. The MIT open source license allows it to be used for academic and commercial projects. CCS CONCEPTS • Applied computing → Annotation.

Research paper thumbnail of New distance and similarity measures for hesitant fuzzy sets and their application in hierarchical clustering

Journal of Intelligent & Fuzzy Systems, 2020

The hesitant fuzzy sets (HFSs) are an extension of the classical fuzzy sets. The membership degre... more The hesitant fuzzy sets (HFSs) are an extension of the classical fuzzy sets. The membership degree of each element in a hesitant fuzzy set can be a set of possible values in the interval [0,1]. On the other hand, distance and similarity measures are important tools in several applications such as pattern recognition, clustering, medical diagnosis, etc. Hence, numerous studies have focused on investigating distance and similarity measures for HFSs. In this paper, some improved distance and similarity measures are introduced for the HFSs, considering the variation range as a hesitance degree for these sets. Comparing the proposed measures to some available distance and similarity measures indicated the better results of the proposed measures. Finally, the application of the proposed measures was investigated in the clustering.

Research paper thumbnail of HFSMOOK-Means: An Improved K-Means Algorithm Using Hesitant Fuzzy Sets and Multi-objective Optimization

Arabian Journal for Science and Engineering, 2020

Clustering is considered as one of the important methods in data mining. The performance of the K... more Clustering is considered as one of the important methods in data mining. The performance of the K-means algorithm, as one of the most common clustering methods, is high sensitivity to the initial cluster centers. Hence, selecting appropriate initial cluster centers for implementing the algorithm improves clustering resulted from the algorithm. The present study aims to find suitable initial cluster centers for the K-means. In fact, the initial cluster centers should be selected in such a way that clusters with high separation and high density can be obtained. Therefore, in this paper, finding initial cluster centers is considered as a multi-objective optimization problem through maximizing the distance between the initial cluster centers, as well as the neighbor density of the initial cluster centers. Solving the above problem through using the MOPSO algorithm provided a set of initial cluster centers of the candidate. Then, the hesitant fuzzy sets were used to evaluate the clusters generated from initial cluster centers by considering separation, cohesion and silhouette index. After that, the concept of informational energy of hesitant fuzzy sets is used, by which non-dominated particles in the Pareto optimal set were ranked and the initial cluster centers were selected for starting the K-means algorithm. The proposed HFSMOOK-means method was compared with several clustering algorithms by considering common and widely used criteria. The results indicated the successful performance of HFSMOOK-means in the majority of the datasets compared to the other algorithms.

Research paper thumbnail of Some results on canonical, cyclic hypergroups and join spaces

In this note, all join spaces associated to fuzzy subsets of a set with three elements, all canon... more In this note, all join spaces associated to fuzzy subsets of a set with three elements, all canonical hypergroups of order 3, spherical join space of order 3 and are characterized.

Research paper thumbnail of New method for rapid diagnosis of Hepatitis disease based on reduction feature and machine learning

Journal of Advanced Computer Science & Technology, 2015

Hepatitis disease is caused by liver injury. Rapid diagnosis of this disease prevents its develop... more Hepatitis disease is caused by liver injury. Rapid diagnosis of this disease prevents its development and suffering to cirrhosis of the liver. Data mining is a new branch of science that helps physicians for proper decision making. In data mining using reduction feature and machine learning algorithms are useful for reducing the complexity of the problem and method of disease diagnosis, respectively. In this study, a new algorithm is proposed for hepatitis diagnosis according to Principal Component Analysis (PCA) and Error Minimized Extreme Learning Machine (EMELM). The algorithm includes two stages; in reduction feature phase, missing records were deleted and hepatitis dataset was normalized in [0,1] range. Thereafter, analysis of the principal component was applied for reduction feature. In classification phase, the reduced dataset is classified using EMELM. For evaluation of the algorithm, hepatitis disease dataset from UCI Machine Learning Repository (University of California) w...

Research paper thumbnail of Problem solving of container loading using genetic algorithm based on modified random keys

Journal of Advanced Computer Science & Technology, 2015

This article presents a solution to the container loading problem. Container loading problem deal... more This article presents a solution to the container loading problem. Container loading problem deals with how to put the cube boxes with different sizes in a container. Our proposed method is based on a particular kind of genetic algorithm based on biased random keys. In the proposed algorithm, we will face generations' extinction. Population decreases with time and with the staircase changes in the rate of elitism, the algorithm is guided towards the global optimum. Biased random keys in the proposed method are provided as discrete. The algorithm also provides the chromosomes that store more than one ability. In order to solve container loading using a placement strategy, due to the size of the boxes and containers, the containers are classified as small units and equal unites in size. Finally the algorithm presented in this paper was compared with three other methods that are based on evolutionary algorithms. The results show that the proposed algorithm has better performance in terms of results and performance time in relation to other methods.

Research paper thumbnail of Classifications of hyper BCK-algebras of order 3

ABSTRACT In this paper we first review the notion of a hyper BCK-algebra, which is a generalizati... more ABSTRACT In this paper we first review the notion of a hyper BCK-algebra, which is a generalization of a BCK-algebra, and we also give some properties of this notion. Then we give the concepts of (strong) hyper BCK-ideals and hyper BCK-algebras, which satisfy the simple or normal conditions. After that, by considering the notion of an isomorphism between two hyper BCK-algebras, we distinguish all hyper BCK-algebras of order 3 which satisfy either the simple condition or the normal condition. In fact there are 19 hyper BCK-algebras of order 3 up to isomorphism.

Research paper thumbnail of The Scrutiny of Variation in the Number of Fuzzy Rules and Membership Functions in a New Genetic-Fuzzy System in Approximation and Prediction Problems

International Journal of Information and Electronics Engineering, 2013

This paper shows a new fuzzy system was improved using genetic algorithm to handle fuzzy inferenc... more This paper shows a new fuzzy system was improved using genetic algorithm to handle fuzzy inference system as a function approximator and time series predictor. The system was developed generality that trained with genetic algorithms (GAs) corresponding to special problem and would be evaluated with different number of rules and membership functions. Then, compare the efficacy of variation of these two parameters in behavior of the system and show the method that achieves an efficient structure in both of them. Also, the proposed GA-Fuzzy inference system successfully predicts a benchmark problem and approximates an introduced function and results have been shown.

Research paper thumbnail of New Similarity Measure Between Two Fuzzy Sets

Journal of Advanced Computational Intelligence and Intelligent Informatics, 2006

We propose a new similarity measure between two fuzzy sets based on their relative sigma count an... more We propose a new similarity measure between two fuzzy sets based on their relative sigma count and extend it to define two other measures, one a similarity measure between elements in fuzzy sets and the second a similarity measure between fuzzy sets in which all elements in the universe of discourse are weighted. We compare our proposal to several previous measures proposed in [1-6].