Sarra Samet, Mohamed Ridda Laouar, Issam Bendib, Sean B. Eom
To increase healthcare quality, early illness prediction helps patients prevent potentially life-threatening health issues before it is too late. Artificial intelligence is a rapidly evolving area, and its applications to diabetes, a worldwide epidemic, have the potential to revolutionize the way diabetes is diagnosed and managed. A total of six supervised machine learning algorithms based on patient data were used and compared to predict the diagnosis of diabetes mellitus. For experiments, the Pima Indians Diabetes Database was used, and their missing values were carefully handled by different techniques. For random train-test splits, the Random Forest classification algorithm achieved an accuracy rate of 92 percent. This model outperforms other state-of-the-art approaches due to the application of a combination of techniques for dealing with missing values (the mixture of imputing missing values techniques) that is proposed. With this approach, the models of this manuscript achieved better accuracy than prior work done with the Pima diabetes data.
{"title":"Analysis and Prediction of Diabetes Disease Using Machine Learning Methods","authors":"Sarra Samet, Mohamed Ridda Laouar, Issam Bendib, Sean B. Eom","doi":"10.4018/ijdsst.303943","DOIUrl":"https://doi.org/10.4018/ijdsst.303943","url":null,"abstract":"To increase healthcare quality, early illness prediction helps patients prevent potentially life-threatening health issues before it is too late. Artificial intelligence is a rapidly evolving area, and its applications to diabetes, a worldwide epidemic, have the potential to revolutionize the way diabetes is diagnosed and managed. A total of six supervised machine learning algorithms based on patient data were used and compared to predict the diagnosis of diabetes mellitus. For experiments, the Pima Indians Diabetes Database was used, and their missing values were carefully handled by different techniques. For random train-test splits, the Random Forest classification algorithm achieved an accuracy rate of 92 percent. This model outperforms other state-of-the-art approaches due to the application of a combination of techniques for dealing with missing values (the mixture of imputing missing values techniques) that is proposed. With this approach, the models of this manuscript achieved better accuracy than prior work done with the Pima diabetes data.","PeriodicalId":42414,"journal":{"name":"International Journal of Decision Support System Technology","volume":"60 1","pages":"1-19"},"PeriodicalIF":1.1,"publicationDate":"2022-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"83691716","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Many real world datasets may contain missing values for various reasons. These incomplete datasets can pose severe issues to the underlying machine learning algorithms and decision support systems. It may result in high computational cost, skewed output and invalid deductions. Various solutions exist to mitigate this issue; the most popular strategy is to estimate the missing values by applying inferential techniques such as linear regression, decision trees or Bayesian inference. In this paper, the missing data problem is discussed in detail with a comprehensive review of the approaches to tackle it. The paper concludes with a discussion on the effectiveness of three imputation methods namely, imputation based on Multiple Linear Regression (MLR), Predictive Mean Matching (PMM) and Classification And Regression Tree (CART) in the context of subspace clustering. The experimental results obtained on real benchmark datasets and high-dimensional synthetic datasets highlight that, MLR based imputation method is more efficient on high-dimensional incomplete datasets.
{"title":"Missing Data Imputation: A Survey","authors":"B. Kelkar","doi":"10.4018/ijdsst.292446","DOIUrl":"https://doi.org/10.4018/ijdsst.292446","url":null,"abstract":"Many real world datasets may contain missing values for various reasons. These incomplete datasets can pose severe issues to the underlying machine learning algorithms and decision support systems. It may result in high computational cost, skewed output and invalid deductions. Various solutions exist to mitigate this issue; the most popular strategy is to estimate the missing values by applying inferential techniques such as linear regression, decision trees or Bayesian inference. In this paper, the missing data problem is discussed in detail with a comprehensive review of the approaches to tackle it. The paper concludes with a discussion on the effectiveness of three imputation methods namely, imputation based on Multiple Linear Regression (MLR), Predictive Mean Matching (PMM) and Classification And Regression Tree (CART) in the context of subspace clustering. The experimental results obtained on real benchmark datasets and high-dimensional synthetic datasets highlight that, MLR based imputation method is more efficient on high-dimensional incomplete datasets.","PeriodicalId":42414,"journal":{"name":"International Journal of Decision Support System Technology","volume":"44 1","pages":"1-20"},"PeriodicalIF":1.1,"publicationDate":"2022-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"81576681","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
F. Zhou, Guiyan Wang, Tianfu Chen, Panpan Ma, S. Pratap
To improve the deployment and optimization of the industrial structure, researchers and practitioners have performed a variety of researches in terms of regional leading industry selection based on AO Hirschman, Rostow and Miyohei’s principles. The criteria and methods employed in previous studies are mainly based on the mass industrial development data, leading to the limitation of study on the application in new high-tech district and underdeveloped regions. Due to lack of industrial data and detail industry information, it is difficult to employ the deterministic regional industry selection model. Therefore, an extended fuzzy-VIKOR approach that the expert-based and trapezoidal fuzzy number decision-making techniques, embedded into the VIKOR steps is proposed. It is developed to solve the regional leading industry selection problems concerning industrial, economic, social and environmental dimensions. Finally, a case study for the industrial planning of a high-tech zone is applied to verify the proposed decision-making approach.
{"title":"Regional Leading Industry Selection Based on an Extended Fuzzy VIKOR Approach","authors":"F. Zhou, Guiyan Wang, Tianfu Chen, Panpan Ma, S. Pratap","doi":"10.4018/ijdsst.286687","DOIUrl":"https://doi.org/10.4018/ijdsst.286687","url":null,"abstract":"To improve the deployment and optimization of the industrial structure, researchers and practitioners have performed a variety of researches in terms of regional leading industry selection based on AO Hirschman, Rostow and Miyohei’s principles. The criteria and methods employed in previous studies are mainly based on the mass industrial development data, leading to the limitation of study on the application in new high-tech district and underdeveloped regions. Due to lack of industrial data and detail industry information, it is difficult to employ the deterministic regional industry selection model. Therefore, an extended fuzzy-VIKOR approach that the expert-based and trapezoidal fuzzy number decision-making techniques, embedded into the VIKOR steps is proposed. It is developed to solve the regional leading industry selection problems concerning industrial, economic, social and environmental dimensions. Finally, a case study for the industrial planning of a high-tech zone is applied to verify the proposed decision-making approach.","PeriodicalId":42414,"journal":{"name":"International Journal of Decision Support System Technology","volume":"40 1","pages":"1-14"},"PeriodicalIF":1.1,"publicationDate":"2022-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"84909809","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
A. R. Alberti, E. A. Frej, Lucia Reis Peixoto Roselli, Murilo Amorim Britto, Evônio Campelo, Adiel Teixeira de Almeida, R. Ferreira
COVID-19 pandemic has put health systems worldwide under pressure. Thus, establish a triage protocol to support the allocation of resources is important to deal with this public health crisis. In this paper, a structured methodology to support the triage of suspected or confirmed COVID-19 patients has been proposed, based on the utilitarian principle. A decision model has been proposed for evaluating three treatment alternatives: intensive care, hospital stay and home isolation. The model is developed according to multi-attribute utility theory and considers two criteria: the life of the patient and the overall cost to the health system. A screening protocol is proposed to support the use of the decision model, and a method is presented for calculating the probability of which of three treatment is the best one. The proposed methodology was implemented in an information and decision system. The originality of this study is using of the multi-attribute utility theory to support the triage of suspected COVID-19 and implement the decision model in an information and decision system.
{"title":"Methodology to Support the Triage of Suspected COVID-19 Patients in Resource-Limited Circumstances","authors":"A. R. Alberti, E. A. Frej, Lucia Reis Peixoto Roselli, Murilo Amorim Britto, Evônio Campelo, Adiel Teixeira de Almeida, R. Ferreira","doi":"10.4018/ijdsst.309993","DOIUrl":"https://doi.org/10.4018/ijdsst.309993","url":null,"abstract":"COVID-19 pandemic has put health systems worldwide under pressure. Thus, establish a triage protocol to support the allocation of resources is important to deal with this public health crisis. In this paper, a structured methodology to support the triage of suspected or confirmed COVID-19 patients has been proposed, based on the utilitarian principle. A decision model has been proposed for evaluating three treatment alternatives: intensive care, hospital stay and home isolation. The model is developed according to multi-attribute utility theory and considers two criteria: the life of the patient and the overall cost to the health system. A screening protocol is proposed to support the use of the decision model, and a method is presented for calculating the probability of which of three treatment is the best one. The proposed methodology was implemented in an information and decision system. The originality of this study is using of the multi-attribute utility theory to support the triage of suspected COVID-19 and implement the decision model in an information and decision system.","PeriodicalId":42414,"journal":{"name":"International Journal of Decision Support System Technology","volume":"1 1","pages":"1-21"},"PeriodicalIF":1.1,"publicationDate":"2022-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"76398229","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Nazanin Vafaei, Rita Almeida Ribeiro, L. Camarinha-Matos
With the fast growing of data-rich systems, dealing with complex decision problems with skewed input data sets and respective outliers is unavoidable. Generally, data skewness refers to a non-uniform distribution in a dataset, i.e. a dataset which contains asymmetries and/or outliers. Normalization is the first step of most multi-criteria decision making (MCDM) problems to obtain dimensionless data, from heterogeneous input data sets, that enable aggregation of criteria and thereby ranking of alternatives. Therefore, when in presence of outliers in criteria datasets, finding a suitable normalization technique is of utmost importance. As such, in this work, we compare seven normalization techniques (Max, Max-Min, Vector, Sum, Logarithmic, Target-based, and Fuzzification) on criteria datasets, which contain outliers to analyse their results for MCDM problems. A numerical example illustrates the behaviour of the chosen normalization techniques and an (ongoing) evaluation assessment framework is used to recommend the best normalization technique for this type of criteria.
{"title":"Comparison of Normalization Techniques on Data Sets With Outliers","authors":"Nazanin Vafaei, Rita Almeida Ribeiro, L. Camarinha-Matos","doi":"10.4018/ijdsst.286184","DOIUrl":"https://doi.org/10.4018/ijdsst.286184","url":null,"abstract":"With the fast growing of data-rich systems, dealing with complex decision problems with skewed input data sets and respective outliers is unavoidable. Generally, data skewness refers to a non-uniform distribution in a dataset, i.e. a dataset which contains asymmetries and/or outliers. Normalization is the first step of most multi-criteria decision making (MCDM) problems to obtain dimensionless data, from heterogeneous input data sets, that enable aggregation of criteria and thereby ranking of alternatives. Therefore, when in presence of outliers in criteria datasets, finding a suitable normalization technique is of utmost importance. As such, in this work, we compare seven normalization techniques (Max, Max-Min, Vector, Sum, Logarithmic, Target-based, and Fuzzification) on criteria datasets, which contain outliers to analyse their results for MCDM problems. A numerical example illustrates the behaviour of the chosen normalization techniques and an (ongoing) evaluation assessment framework is used to recommend the best normalization technique for this type of criteria.","PeriodicalId":42414,"journal":{"name":"International Journal of Decision Support System Technology","volume":"2 1","pages":"1-17"},"PeriodicalIF":1.1,"publicationDate":"2022-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"91170275","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Fen Wang, M. Raisinghani, Manuel Mora Tavarez, J. Forrest
This study conducts a review and synthesis of the Business Intelligence and Analytics (BI&A) evolution, applications, frameworks and emerging trends with the aim to provide a summary of core concepts, a succinct but valuable description of main applications and frameworks, and an account of main recommendations for addressing the Big Data challenges and opportunities. It develops an integrated and organized view on the BI&A evolution process and presents an integrated BI&A application framework to help organizations adopt or develop the appropriate BI&A solutions to derive the desired impact in the Big Data era. This paper also elicits a set of practical recommendations to executives and leaders in organizations worldwide for interpreting the BI&A literature and applying the rich body of knowledge for IT practitioners. It traces the BI&A evolution to data-driven discovery and highly proactive and creative decision-making utilizing advanced analytical techniques with unstructured and massive data sources to cope with a highly dynamic global business environment in the Big Data era.
{"title":"Effective Decision Support in the Big Data Era: Optimize Organizational Performance via BI&A","authors":"Fen Wang, M. Raisinghani, Manuel Mora Tavarez, J. Forrest","doi":"10.4018/ijdsst.286683","DOIUrl":"https://doi.org/10.4018/ijdsst.286683","url":null,"abstract":"This study conducts a review and synthesis of the Business Intelligence and Analytics (BI&A) evolution, applications, frameworks and emerging trends with the aim to provide a summary of core concepts, a succinct but valuable description of main applications and frameworks, and an account of main recommendations for addressing the Big Data challenges and opportunities. It develops an integrated and organized view on the BI&A evolution process and presents an integrated BI&A application framework to help organizations adopt or develop the appropriate BI&A solutions to derive the desired impact in the Big Data era. This paper also elicits a set of practical recommendations to executives and leaders in organizations worldwide for interpreting the BI&A literature and applying the rich body of knowledge for IT practitioners. It traces the BI&A evolution to data-driven discovery and highly proactive and creative decision-making utilizing advanced analytical techniques with unstructured and massive data sources to cope with a highly dynamic global business environment in the Big Data era.","PeriodicalId":42414,"journal":{"name":"International Journal of Decision Support System Technology","volume":"1 1","pages":"1-16"},"PeriodicalIF":1.1,"publicationDate":"2022-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"83157501","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Iwasokun Gabriel Babatunde, Ayowole Oluwatayo Idowu, B. Kuboye
The traditional ways of candidate selection and recruitment are prone to subjectivity, imprecision and vagueness. With a view to achieving objective and precise selection and recruitment while keeping up with technological improvement and changes, this paper discusses a fuzzification-based technique for candidate rating and selection. The technique comprises a fuzzy logic component that is an extension of Boolean logic and used for establishing accurate selection process and precise solutions to multi-variable problems. There is a knowledge base component which forms the database of multi-level information and rule base which composes a set of if-then statements for decision making. Its inference engine applies a pre-defined procedure on input from the rule base and fuzzy logic interfaces for final recommendations. The proposed methodology performs pre-defined procedures that are based on some input sets which stores multi-level information derived from several pre-specified scores. Results from the implementation of the proposed technique established its practical function.
{"title":"Fuzzification Technique for Candidate Rating and Selection","authors":"Iwasokun Gabriel Babatunde, Ayowole Oluwatayo Idowu, B. Kuboye","doi":"10.4018/ijdsst.303944","DOIUrl":"https://doi.org/10.4018/ijdsst.303944","url":null,"abstract":"The traditional ways of candidate selection and recruitment are prone to subjectivity, imprecision and vagueness. With a view to achieving objective and precise selection and recruitment while keeping up with technological improvement and changes, this paper discusses a fuzzification-based technique for candidate rating and selection. The technique comprises a fuzzy logic component that is an extension of Boolean logic and used for establishing accurate selection process and precise solutions to multi-variable problems. There is a knowledge base component which forms the database of multi-level information and rule base which composes a set of if-then statements for decision making. Its inference engine applies a pre-defined procedure on input from the rule base and fuzzy logic interfaces for final recommendations. The proposed methodology performs pre-defined procedures that are based on some input sets which stores multi-level information derived from several pre-specified scores. Results from the implementation of the proposed technique established its practical function.","PeriodicalId":42414,"journal":{"name":"International Journal of Decision Support System Technology","volume":"21 1","pages":"1-23"},"PeriodicalIF":1.1,"publicationDate":"2022-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"84398945","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Attendance management can become a tedious task for teachers if it is performed manually.. This problem can be solved with the help of an automatic attendance management system. But validation is one of the main issues in the system. Generally, biometrics are used in the smart automatic attendance system. Managing attendance with the help of face recognition is one of the biometric methods with better efficiency as compared to others. Smart Attendance with the help of instant face recognition is a real-life solution that helps in handling daily life activities and maintaining a student attendance system. Face recognition-based attendance system uses face biometrics which is based on high resolution monitor video and other technologies to recognize the face of the student. In project, the system will be able to find and recognize human faces fast and accurately with the help of images or videos that will be captured through a surveillance camera. It will convert the frames of the video into images so that our system can easily search that image in the attendance database.
{"title":"Algorithmic Analysis of Automatic Attendance System Using Facial Recognition: A Revolutionary Approach for Future Education","authors":"Rohit Rastogi, Abhinav Tyagi, Himanshu Upadhyay, Devendra Singh","doi":"10.4018/ijdsst.286688","DOIUrl":"https://doi.org/10.4018/ijdsst.286688","url":null,"abstract":"Attendance management can become a tedious task for teachers if it is performed manually.. This problem can be solved with the help of an automatic attendance management system. But validation is one of the main issues in the system. Generally, biometrics are used in the smart automatic attendance system. Managing attendance with the help of face recognition is one of the biometric methods with better efficiency as compared to others. Smart Attendance with the help of instant face recognition is a real-life solution that helps in handling daily life activities and maintaining a student attendance system. Face recognition-based attendance system uses face biometrics which is based on high resolution monitor video and other technologies to recognize the face of the student. In project, the system will be able to find and recognize human faces fast and accurately with the help of images or videos that will be captured through a surveillance camera. It will convert the frames of the video into images so that our system can easily search that image in the attendance database.","PeriodicalId":42414,"journal":{"name":"International Journal of Decision Support System Technology","volume":"55 99 1","pages":"1-19"},"PeriodicalIF":1.1,"publicationDate":"2022-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"80747440","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
A deterministic decision support system is developed for the assessment of various Indian cities based on the air quality parameters in this research. The present study shapes the assessment of cities as a multi-criteria decision making (MCDM) problem due to the involvement of many indicators. To solve the present assessment problem, an MCDM method, namely, Distance based approach (DBA) that mainly works on the Euclidean distance calculation for each city from the optimal point and ranks the cities on the basis of their calculated distances. The city scoring minimum distance value is ranked at top position and the city with the maximum distance value on the last position.
本研究开发了一套基于空气质量参数的确定性决策支持系统，用于评估印度各城市的空气质量。由于涉及许多指标，本研究将城市评估塑造为一个多标准决策问题。为了解决目前的评价问题，提出了一种MCDM方法，即基于距离的方法(Distance based approach, DBA)，该方法主要从最优点开始对每个城市进行欧氏距离计算，并根据计算出的距离对城市进行排名。距离值最小的城市排在首位，距离值最大的城市排在最后一位。
{"title":"Deterministic Decision Support System for the Assessment of Cities Based on Air Quality Indicators: Decision Support System Using DBA","authors":"R. Garg, Supriya Raheja","doi":"10.4018/ijdsst.292448","DOIUrl":"https://doi.org/10.4018/ijdsst.292448","url":null,"abstract":"A deterministic decision support system is developed for the assessment of various Indian cities based on the air quality parameters in this research. The present study shapes the assessment of cities as a multi-criteria decision making (MCDM) problem due to the involvement of many indicators. To solve the present assessment problem, an MCDM method, namely, Distance based approach (DBA) that mainly works on the Euclidean distance calculation for each city from the optimal point and ranks the cities on the basis of their calculated distances. The city scoring minimum distance value is ranked at top position and the city with the maximum distance value on the last position.","PeriodicalId":42414,"journal":{"name":"International Journal of Decision Support System Technology","volume":"45 1","pages":"1-20"},"PeriodicalIF":1.1,"publicationDate":"2022-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"80965204","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Umberto Di Giacomo, F. Mercaldo, A. Santone, Giovanni Capobianco
During the last few years, sports analytics has been growing rapidly. The main usage of this discipline is the prediction of soccer match results, even if it can be applied with interesting results in different areas, such as analysis based on the player position information. In this paper, we propose an approach aimed to recognize the player position in a soccer match, predicting the specific zone in which the player is located in a specific moment. Similar objectives have never been considered yet with our best knowledge. We consider supervised machine learning techniques by considering a dataset obtained through video capturing and tracking system. The data analyzed refer to several professional soccer games captured at the Alfheim Stadium in Tromso, Norway. The approach can be used in real-time, in order to verify if a player is playing according to the guidelines of the coach. In the experimental analysis, three different types of classification have been performed, i.e., three different divisions of the field, reaching the best results with Random Tree Algorithm.
{"title":"Machine Learning on Soccer Player Positions","authors":"Umberto Di Giacomo, F. Mercaldo, A. Santone, Giovanni Capobianco","doi":"10.4018/ijdsst.286678","DOIUrl":"https://doi.org/10.4018/ijdsst.286678","url":null,"abstract":"During the last few years, sports analytics has been growing rapidly. The main usage of this discipline is the prediction of soccer match results, even if it can be applied with interesting results in different areas, such as analysis based on the player position information. In this paper, we propose an approach aimed to recognize the player position in a soccer match, predicting the specific zone in which the player is located in a specific moment. Similar objectives have never been considered yet with our best knowledge. We consider supervised machine learning techniques by considering a dataset obtained through video capturing and tracking system. The data analyzed refer to several professional soccer games captured at the Alfheim Stadium in Tromso, Norway. The approach can be used in real-time, in order to verify if a player is playing according to the guidelines of the coach. In the experimental analysis, three different types of classification have been performed, i.e., three different divisions of the field, reaching the best results with Random Tree Algorithm.","PeriodicalId":42414,"journal":{"name":"International Journal of Decision Support System Technology","volume":"10 1","pages":"1-19"},"PeriodicalIF":1.1,"publicationDate":"2022-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"79880636","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：