Pub Date : 2021-09-22DOI: 10.1142/s0219622021500516
A. Yosef, Moti Schneider, E. Shnaider
In this study, we introduce a data mining method to identify biased and/or misleading outlooks for future performance of various factors, such as income, corporate profits, production, countries’ GDP, etc. The method consists of several components. One very important component involves building a general model, where the dependent variable is a factor suspected of projecting an over-optimistic impression in some records. Explanatory variables in the model are viewed as representing the potential for the satisfactory performance of the dependent variable. The second component involves evaluating the potential for the individual records of interest (specific countries, corporations, production facilities, etc.), and allows us to identify possible gaps between the upbeat/optimistic projections into the future (of the dependent variable) versus low and/or declining potential. In other words, low and/or declining potential basically tells us that the optimistic future performance of the dependent variable is unattainable, and could also represent misleading or deceitful information. The important novelty of this study is the capability to identify a highly exaggerated outlook of future performance, by utilizing a soft regression tool and the concept of “performance potential”. The process is explained in detail, including the conditions for successful evaluations. Case studies to evaluate expected economic success are presented.
{"title":"Data Mining Method for Identifying Biased or Misleading Future Outlook","authors":"A. Yosef, Moti Schneider, E. Shnaider","doi":"10.1142/s0219622021500516","DOIUrl":"https://doi.org/10.1142/s0219622021500516","url":null,"abstract":"In this study, we introduce a data mining method to identify biased and/or misleading outlooks for future performance of various factors, such as income, corporate profits, production, countries’ GDP, etc. The method consists of several components. One very important component involves building a general model, where the dependent variable is a factor suspected of projecting an over-optimistic impression in some records. Explanatory variables in the model are viewed as representing the potential for the satisfactory performance of the dependent variable. The second component involves evaluating the potential for the individual records of interest (specific countries, corporations, production facilities, etc.), and allows us to identify possible gaps between the upbeat/optimistic projections into the future (of the dependent variable) versus low and/or declining potential. In other words, low and/or declining potential basically tells us that the optimistic future performance of the dependent variable is unattainable, and could also represent misleading or deceitful information. The important novelty of this study is the capability to identify a highly exaggerated outlook of future performance, by utilizing a soft regression tool and the concept of “performance potential”. The process is explained in detail, including the conditions for successful evaluations. Case studies to evaluate expected economic success are presented.","PeriodicalId":13527,"journal":{"name":"Int. J. Inf. Technol. Decis. Mak.","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2021-09-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"88124574","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}
Pub Date : 2021-09-22DOI: 10.1142/s0219622021500590
K. Kabassi
Websites of environmental content constitute an important tool for promoting environmental information, affect environmental attitudes and promote protected areas as touristic destinations. However, these websites have to be evaluated to ensure that they reach their final goal. The use of multi-criteria decision-making (MCDM) models in website evaluation is relatively new and not many models have been tested for this purpose. Comparisons of such models have been implemented in various domains but not for the purposes of environmental website evaluation. The main objective of this paper is on presenting the procedure of comparison of MCDM models spherical by providing in detail the steps that have to be followed. This process was implemented for website evaluation and investigated the comparative performance of the TOPSIS and VIKOR models. This comparison process involves reliability analysis of the questionnaire and the sample of decision makers, pairwise comparisons of the models by calculating the Pearson correlation coefficient and estimation of the Cohen’s Kappa for testing the inter-rater comparability, using the models as raters. Furthermore, a sensitivity and robustness analysis of those models is implemented, which also has not been implemented before in the application of those models in website evaluation. The tests implemented and presented in this paper reveal that the reasonable disagreement that was often observed among the methods did not affect their reliability. As a result, MCDM models proved very effective for evaluating websites of environmental content.
{"title":"Comparison of Multi-Criteria Decision-Making Models: Analyzing the Steps in the Domain of Websites' Evaluation","authors":"K. Kabassi","doi":"10.1142/s0219622021500590","DOIUrl":"https://doi.org/10.1142/s0219622021500590","url":null,"abstract":"Websites of environmental content constitute an important tool for promoting environmental information, affect environmental attitudes and promote protected areas as touristic destinations. However, these websites have to be evaluated to ensure that they reach their final goal. The use of multi-criteria decision-making (MCDM) models in website evaluation is relatively new and not many models have been tested for this purpose. Comparisons of such models have been implemented in various domains but not for the purposes of environmental website evaluation. The main objective of this paper is on presenting the procedure of comparison of MCDM models spherical by providing in detail the steps that have to be followed. This process was implemented for website evaluation and investigated the comparative performance of the TOPSIS and VIKOR models. This comparison process involves reliability analysis of the questionnaire and the sample of decision makers, pairwise comparisons of the models by calculating the Pearson correlation coefficient and estimation of the Cohen’s Kappa for testing the inter-rater comparability, using the models as raters. Furthermore, a sensitivity and robustness analysis of those models is implemented, which also has not been implemented before in the application of those models in website evaluation. The tests implemented and presented in this paper reveal that the reasonable disagreement that was often observed among the methods did not affect their reliability. As a result, MCDM models proved very effective for evaluating websites of environmental content.","PeriodicalId":13527,"journal":{"name":"Int. J. Inf. Technol. Decis. Mak.","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2021-09-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"85355172","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}
Pub Date : 2021-09-20DOI: 10.1142/s0219622021500607
Onur Doğan, O. Seymen, Abdulkadir Hiziroglu
The vast quantity of customer data and its ubiquity, as well as the inabilities of conventional segmentation tools, have diverted researchers in search of powerful segmentation techniques for generating managerially meaningful information. Due to its noteworthy practical use, soft computing-based techniques, especially fuzzy clustering, can be considered one of those contemporary approaches. Although there have been various fuzzy-based clustering applications in segmentation, intuitionistic fuzzy sets that have the complimentary feature have appeared in limited studies, especially in a comparative context. Therefore, this study extends the current body of the pertaining literature by providing a comparative assessment of intuitionistic fuzzy clustering. The comparison was carried out with two other well-known segmentation techniques, [Formula: see text]-means and fuzzy [Formula: see text]-means, based on transaction data that belong to Turkey’s two major cities. Over 10,000 records of customers’ data were processed for segmentation purposes, and the comparative approaches were presented. According to the results, the intuitionistic fuzzy clustering approach outperformed the other methods in terms of the clustering efficiency index being utilized. The validity of the segmentation structure obtained by the superior approach was ensured via nonsegmentation variables. The comparative assessment and the potential managerial implications could be considered as a contribution to the corresponding literature. This study also compares the effects of the different parameter values used in the proposed model.
{"title":"Customer Behavior Analysis by Intuitionistic Fuzzy Segmentation: Comparison of Two Major Cities in Turkey","authors":"Onur Doğan, O. Seymen, Abdulkadir Hiziroglu","doi":"10.1142/s0219622021500607","DOIUrl":"https://doi.org/10.1142/s0219622021500607","url":null,"abstract":"The vast quantity of customer data and its ubiquity, as well as the inabilities of conventional segmentation tools, have diverted researchers in search of powerful segmentation techniques for generating managerially meaningful information. Due to its noteworthy practical use, soft computing-based techniques, especially fuzzy clustering, can be considered one of those contemporary approaches. Although there have been various fuzzy-based clustering applications in segmentation, intuitionistic fuzzy sets that have the complimentary feature have appeared in limited studies, especially in a comparative context. Therefore, this study extends the current body of the pertaining literature by providing a comparative assessment of intuitionistic fuzzy clustering. The comparison was carried out with two other well-known segmentation techniques, [Formula: see text]-means and fuzzy [Formula: see text]-means, based on transaction data that belong to Turkey’s two major cities. Over 10,000 records of customers’ data were processed for segmentation purposes, and the comparative approaches were presented. According to the results, the intuitionistic fuzzy clustering approach outperformed the other methods in terms of the clustering efficiency index being utilized. The validity of the segmentation structure obtained by the superior approach was ensured via nonsegmentation variables. The comparative assessment and the potential managerial implications could be considered as a contribution to the corresponding literature. This study also compares the effects of the different parameter values used in the proposed model.","PeriodicalId":13527,"journal":{"name":"Int. J. Inf. Technol. Decis. Mak.","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2021-09-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"86947547","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}
Pub Date : 2021-09-17DOI: 10.1142/s0219622021500619
C. Iwendi, Ebuka Ibeke, Harshini Eggoni, Sreerajavenkatareddy Velagala, Gautam Srivastava
The creation of digital marketing has enabled companies to adopt personalized item recommendations for their customers. This process keeps them ahead of the competition. One of the techniques used in item recommendation is known as item-based recommendation system or item–item collaborative filtering. Presently, item recommendation is based completely on ratings like 1–5, which is not included in the comment section. In this context, users or customers express their feelings and thoughts about products or services. This paper proposes a machine learning model system where 0, 2, 4 are used to rate products. 0 is negative, 2 is neutral, 4 is positive. This will be in addition to the existing review system that takes care of the users’ reviews and comments, without disrupting it. We have implemented this model by using Keras, Pandas and Sci-kit Learning libraries to run the internal work. The proposed approach improved prediction with [Formula: see text] accuracy for Yelp datasets of businesses across 11 metropolitan areas in four countries, along with a mean absolute error (MAE) of [Formula: see text], precision at [Formula: see text], recall at [Formula: see text] and F1-Score at [Formula: see text]. Our model shows scalability advantage and how organizations can revolutionize their recommender systems to attract possible customers and increase patronage. Also, the proposed similarity algorithm was compared to conventional algorithms to estimate its performance and accuracy in terms of its root mean square error (RMSE), precision and recall. Results of this experiment indicate that the similarity recommendation algorithm performs better than the conventional algorithm and enhances recommendation accuracy.
{"title":"Pointer-Based Item-to-Item Collaborative Filtering Recommendation System Using a Machine Learning Model","authors":"C. Iwendi, Ebuka Ibeke, Harshini Eggoni, Sreerajavenkatareddy Velagala, Gautam Srivastava","doi":"10.1142/s0219622021500619","DOIUrl":"https://doi.org/10.1142/s0219622021500619","url":null,"abstract":"The creation of digital marketing has enabled companies to adopt personalized item recommendations for their customers. This process keeps them ahead of the competition. One of the techniques used in item recommendation is known as item-based recommendation system or item–item collaborative filtering. Presently, item recommendation is based completely on ratings like 1–5, which is not included in the comment section. In this context, users or customers express their feelings and thoughts about products or services. This paper proposes a machine learning model system where 0, 2, 4 are used to rate products. 0 is negative, 2 is neutral, 4 is positive. This will be in addition to the existing review system that takes care of the users’ reviews and comments, without disrupting it. We have implemented this model by using Keras, Pandas and Sci-kit Learning libraries to run the internal work. The proposed approach improved prediction with [Formula: see text] accuracy for Yelp datasets of businesses across 11 metropolitan areas in four countries, along with a mean absolute error (MAE) of [Formula: see text], precision at [Formula: see text], recall at [Formula: see text] and F1-Score at [Formula: see text]. Our model shows scalability advantage and how organizations can revolutionize their recommender systems to attract possible customers and increase patronage. Also, the proposed similarity algorithm was compared to conventional algorithms to estimate its performance and accuracy in terms of its root mean square error (RMSE), precision and recall. Results of this experiment indicate that the similarity recommendation algorithm performs better than the conventional algorithm and enhances recommendation accuracy.","PeriodicalId":13527,"journal":{"name":"Int. J. Inf. Technol. Decis. Mak.","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2021-09-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"84898016","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}
Pub Date : 2021-09-17DOI: 10.1142/s0219622021500565
Igor Pinheiro de Araújo Costa, M. Moreira, Arthur Pinheiro de Araújo Costa, L. F. H. D. S. D. B. Teixeira, C. F. Gomes, M. Santos
The globalization of business and the consequent exposure to global competition, besides the economic and social changes caused by the COVID-19 pandemic made the Training & Development (T&D) sector increasingly important for professionals in the corporate environment. In this sense, managing stakeholders and a portfolio of clients, as well as analyzing the relationship between customer and service, are necessary and strategic for the success of professional training organizations. This paper aims to support the strategic process of portfolio formation of T&D courses offered by a company in the Information Technology (IT) training sector in Brazil, through the application of the ELECTRE-MOr multicriteria sorting method. We have obtained a categorization of several courses, aiming to define which ones should be prioritized, maintained, or discarded by the company’s management. The results showed that, among the analyzed courses, only 17% should be prioritized, 61% maintained, and 22% discarded by the company.
{"title":"Strategic Study for Managing the Portfolio of IT Courses Offered by a Corporate Training Company: An Approach in the Light of the ELECTRE-MOr Multicriteria Hybrid Method","authors":"Igor Pinheiro de Araújo Costa, M. Moreira, Arthur Pinheiro de Araújo Costa, L. F. H. D. S. D. B. Teixeira, C. F. Gomes, M. Santos","doi":"10.1142/s0219622021500565","DOIUrl":"https://doi.org/10.1142/s0219622021500565","url":null,"abstract":"The globalization of business and the consequent exposure to global competition, besides the economic and social changes caused by the COVID-19 pandemic made the Training & Development (T&D) sector increasingly important for professionals in the corporate environment. In this sense, managing stakeholders and a portfolio of clients, as well as analyzing the relationship between customer and service, are necessary and strategic for the success of professional training organizations. This paper aims to support the strategic process of portfolio formation of T&D courses offered by a company in the Information Technology (IT) training sector in Brazil, through the application of the ELECTRE-MOr multicriteria sorting method. We have obtained a categorization of several courses, aiming to define which ones should be prioritized, maintained, or discarded by the company’s management. The results showed that, among the analyzed courses, only 17% should be prioritized, 61% maintained, and 22% discarded by the company.","PeriodicalId":13527,"journal":{"name":"Int. J. Inf. Technol. Decis. Mak.","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2021-09-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"80163795","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}
Pub Date : 2021-09-17DOI: 10.1142/s0219622021500474
S. Hekmat, M. Amiri, Golshan Madraki
Our goal is to address the complicated problem of strategic supplier selection with interrelated and insufficient data. To achieve this goal, we proposed our Strategic Supplier Selection Methodology (SSSM). First, SSSM formulates the enterprise strategies and evaluation criteria. Then, we developed a novel method called Grey Principal Component Analysis-Data Envelopment Analysis (GPCA-DEA) to evaluate suppliers in SSSM. GPCA-DEA overcomes the major disadvantages and limitations of former methodologies (e.g., DEA) while dealing with insufficient and interrelated data. Finally, SSSM applies Multiple Attribute Decision-Making (MADM) methods to select suppliers based on the ranking score. The application of SSSM is illustrated in the payment industry to select Payment Initiation Service Providers (PISP). For the first time, we considered the payment industry-specific criteria in compliance with the latest regulation (PSD2). The Spearman rank correlation statistical test showed that our method (GPCA-DEA used in SSSM) yields more reliable results than a former version of DEA.
{"title":"Strategic Supplier Selection in Payment Industry: A Multi-Criteria Solution for Insufficient and Interrelated Data Sources","authors":"S. Hekmat, M. Amiri, Golshan Madraki","doi":"10.1142/s0219622021500474","DOIUrl":"https://doi.org/10.1142/s0219622021500474","url":null,"abstract":"Our goal is to address the complicated problem of strategic supplier selection with interrelated and insufficient data. To achieve this goal, we proposed our Strategic Supplier Selection Methodology (SSSM). First, SSSM formulates the enterprise strategies and evaluation criteria. Then, we developed a novel method called Grey Principal Component Analysis-Data Envelopment Analysis (GPCA-DEA) to evaluate suppliers in SSSM. GPCA-DEA overcomes the major disadvantages and limitations of former methodologies (e.g., DEA) while dealing with insufficient and interrelated data. Finally, SSSM applies Multiple Attribute Decision-Making (MADM) methods to select suppliers based on the ranking score. The application of SSSM is illustrated in the payment industry to select Payment Initiation Service Providers (PISP). For the first time, we considered the payment industry-specific criteria in compliance with the latest regulation (PSD2). The Spearman rank correlation statistical test showed that our method (GPCA-DEA used in SSSM) yields more reliable results than a former version of DEA.","PeriodicalId":13527,"journal":{"name":"Int. J. Inf. Technol. Decis. Mak.","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2021-09-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"74303528","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}
Pub Date : 2021-09-15DOI: 10.1142/s0219622021500577
E. Fernández, Jorge Navarro, Efrain Solares
Decision-making problems often require characterization of alternatives through multiple criteria. In contexts where some of these criteria interact, the decision maker (DM) must consider the interaction effects during the aggregation of criteria scores. The well-known ELECTRE (ELimination Et Choix Traduisant la REalité) methods were recently improved to deal with interacting criteria fulfilling several relevant properties, addressing the main types of interaction, and retaining most of the fundamental characteristics of the classical methods. An important criticism to such a family of methods is that defining its parameter values is often difficult and can involve significant challenges and high cognitive effort for the DM; this is exacerbated in the improved version whose parameters are even less intuitive. Here, we describe an evolutionary-based method in which parameter values are inferred by exploiting easy-to-make decisions made or accepted by the DM, thereby reducing his/her cognitive effort. A genetic algorithm is proposed to solve a regression-inspired nonlinear optimization problem. To the best of our knowledge, this is the first paper addressing the indirect elicitation of the ELECTRE model’s parameters with interacting criteria. The proposal is assessed through both in-sample and out-of-sample experiments. Statistical tests indicate robustness of the proposal in terms of the number of criteria and their possible interactions. Results show almost perfect effectiveness to reproduce the DM’s preferences in all situations.
决策问题通常需要通过多个标准来描述备选方案。在其中一些标准相互作用的环境中，决策者(DM)必须在标准分数聚合期间考虑相互作用的影响。众所周知的ELECTRE (ELimination Et Choix Traduisant la realit)方法最近得到了改进，以处理满足几个相关属性的相互作用标准，解决了相互作用的主要类型，并保留了经典方法的大多数基本特征。对此类方法族的一个重要批评是，定义其参数值通常很困难，并且可能涉及DM的重大挑战和高认知努力;这在参数更不直观的改进版本中更加严重。在这里，我们描述了一种基于进化的方法，其中参数值是通过利用DM做出或接受的易于做出的决策来推断的，从而减少了他/她的认知努力。提出了一种遗传算法来解决回归启发的非线性优化问题。据我们所知，这是第一篇用相互作用标准间接引出ELECTRE模型参数的论文。通过样本内和样本外实验对该方案进行了评估。统计检验表明，就标准数量及其可能的相互作用而言，该提案具有稳健性。结果显示，在所有情况下复制DM偏好的效果几乎是完美的。
{"title":"Decision-Making with Multiple Interacting Criteria: An Indirect Elicitation of Preference Parameters Using Evolutionary Algorithms","authors":"E. Fernández, Jorge Navarro, Efrain Solares","doi":"10.1142/s0219622021500577","DOIUrl":"https://doi.org/10.1142/s0219622021500577","url":null,"abstract":"Decision-making problems often require characterization of alternatives through multiple criteria. In contexts where some of these criteria interact, the decision maker (DM) must consider the interaction effects during the aggregation of criteria scores. The well-known ELECTRE (ELimination Et Choix Traduisant la REalité) methods were recently improved to deal with interacting criteria fulfilling several relevant properties, addressing the main types of interaction, and retaining most of the fundamental characteristics of the classical methods. An important criticism to such a family of methods is that defining its parameter values is often difficult and can involve significant challenges and high cognitive effort for the DM; this is exacerbated in the improved version whose parameters are even less intuitive. Here, we describe an evolutionary-based method in which parameter values are inferred by exploiting easy-to-make decisions made or accepted by the DM, thereby reducing his/her cognitive effort. A genetic algorithm is proposed to solve a regression-inspired nonlinear optimization problem. To the best of our knowledge, this is the first paper addressing the indirect elicitation of the ELECTRE model’s parameters with interacting criteria. The proposal is assessed through both in-sample and out-of-sample experiments. Statistical tests indicate robustness of the proposal in terms of the number of criteria and their possible interactions. Results show almost perfect effectiveness to reproduce the DM’s preferences in all situations.","PeriodicalId":13527,"journal":{"name":"Int. J. Inf. Technol. Decis. Mak.","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2021-09-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"91014576","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}
Broad Learning System (BLS) has been proven to be one of the most important techniques for classification and regression in machine learning and data mining. BLS directly collects all the features from feature and enhancement nodes as input of the output layer, which neglects vast amounts of redundant information. It usually leads to be inefficient and overfitting. To resolve this issue, we propose sparse regularization-based compact broad learning system (CBLS) framework, which can simultaneously remove redundant nodes and weights. To be more specific, we use group sparse regularization based on [Formula: see text] norm to promote the competition between different nodes and then remove redundant nodes, and a class of nonconvex sparsity regularization to promote the competition between different weights and then remove redundant weights. To optimize the resulting problem of the proposed CBLS, we exploit an efficient alternative optimization algorithm based on proximal gradient method together with computational complexity. Finally, extensive experiments on the classification task are conducted on public benchmark datasets to verify the effectiveness and superiority of the proposed CBLS.
广义学习系统(BLS)已被证明是机器学习和数据挖掘中最重要的分类和回归技术之一。BLS直接收集特征和增强节点的所有特征作为输出层的输入，忽略了大量的冗余信息。它通常会导致效率低下和过拟合。为了解决这个问题，我们提出了基于稀疏正则化的紧凑广义学习系统(CBLS)框架，该框架可以同时去除冗余节点和权值。具体来说，我们使用基于[Formula: see text]范数的组稀疏正则化来促进不同节点之间的竞争进而去除冗余节点，使用一类非凸稀疏正则化来促进不同权值之间的竞争进而去除冗余权值。为了优化所提出的CBLS的结果问题，我们利用了一种有效的基于近端梯度法的替代优化算法，并考虑了计算复杂度。最后，在公共基准数据集上对分类任务进行了大量实验，验证了所提CBLS的有效性和优越性。
{"title":"Towards Compact Broad Learning System by Combined Sparse Regularization","authors":"Jianyu Miao, Tiejun Yang, Junwei Jin, Lijun Sun, Lingfeng Niu, Yong Shi","doi":"10.1142/s0219622021500553","DOIUrl":"https://doi.org/10.1142/s0219622021500553","url":null,"abstract":"Broad Learning System (BLS) has been proven to be one of the most important techniques for classification and regression in machine learning and data mining. BLS directly collects all the features from feature and enhancement nodes as input of the output layer, which neglects vast amounts of redundant information. It usually leads to be inefficient and overfitting. To resolve this issue, we propose sparse regularization-based compact broad learning system (CBLS) framework, which can simultaneously remove redundant nodes and weights. To be more specific, we use group sparse regularization based on [Formula: see text] norm to promote the competition between different nodes and then remove redundant nodes, and a class of nonconvex sparsity regularization to promote the competition between different weights and then remove redundant weights. To optimize the resulting problem of the proposed CBLS, we exploit an efficient alternative optimization algorithm based on proximal gradient method together with computational complexity. Finally, extensive experiments on the classification task are conducted on public benchmark datasets to verify the effectiveness and superiority of the proposed CBLS.","PeriodicalId":13527,"journal":{"name":"Int. J. Inf. Technol. Decis. Mak.","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2021-09-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"82042590","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}
Pub Date : 2021-08-30DOI: 10.1142/s021962202150053x
Linda Elmhadhbi, Mohamed-Hedi Karray, B. Archimède, J. Otte, Barry Smith
In light of the complexity of unfolding disasters, the diversity of rapidly evolving events, the enormous amount of generated information, and the huge pool of casualties, emergency responders (ERs) may be overwhelmed and in consequence poor decisions may be made. In fact, the possibility of transporting the wounded victims to one of several hospitals and the dynamic changes in healthcare resource availability make the decision process more complex. To tackle this problem, we propose a multicriteria decision support service, based on the Analytic Hierarchy Process (AHP) method, that aims to avoid overcrowding and outpacing the capacity of a hospital to effectively provide the best care to victims by finding out the most appropriate hospital that meets the victims’ needs. The proposed approach searches for the most appropriate healthcare institution that can effectively deal with the victims’ needs by considering the availability of the needed resources in the hospital, the victim’s wait time to receive the healthcare, and the transfer time that represents the hospital proximity to the disaster site. The evaluation and validation results showed that the assignment of hospitals was done successfully considering the needs of each victim and without overwhelming any single hospital.
{"title":"Ontology-Driven Multicriteria Decision Support for Victim Evacuation","authors":"Linda Elmhadhbi, Mohamed-Hedi Karray, B. Archimède, J. Otte, Barry Smith","doi":"10.1142/s021962202150053x","DOIUrl":"https://doi.org/10.1142/s021962202150053x","url":null,"abstract":"In light of the complexity of unfolding disasters, the diversity of rapidly evolving events, the enormous amount of generated information, and the huge pool of casualties, emergency responders (ERs) may be overwhelmed and in consequence poor decisions may be made. In fact, the possibility of transporting the wounded victims to one of several hospitals and the dynamic changes in healthcare resource availability make the decision process more complex. To tackle this problem, we propose a multicriteria decision support service, based on the Analytic Hierarchy Process (AHP) method, that aims to avoid overcrowding and outpacing the capacity of a hospital to effectively provide the best care to victims by finding out the most appropriate hospital that meets the victims’ needs. The proposed approach searches for the most appropriate healthcare institution that can effectively deal with the victims’ needs by considering the availability of the needed resources in the hospital, the victim’s wait time to receive the healthcare, and the transfer time that represents the hospital proximity to the disaster site. The evaluation and validation results showed that the assignment of hospitals was done successfully considering the needs of each victim and without overwhelming any single hospital.","PeriodicalId":13527,"journal":{"name":"Int. J. Inf. Technol. Decis. Mak.","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2021-08-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"86055482","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}
Pub Date : 2021-08-23DOI: 10.1142/s0219622021500528
Mohanad A. Deif, A. Solyman, Rania E. Hammam
This paper presents a forecasting model for the mortality rates of COVID-19 in six of the top most affected countries depending on the hybrid Genetic Algorithm and Autoregressive Integrated Moving Average (GA-ARIMA). It was aimed to develop an advanced and reliable predicting model that provides future forecasts of possible confirmed cases and mortality rates (Total Deaths per 1 million Population of COVID-19) that could help the public health authorities to develop plans required to resolve the crisis of the pandemic threat in a timely and efficient manner. The study focused on predicting the mortality rates of COVID-19 because the mortality rate determines the prevalence of highly contagious diseases. The Genetic algorithm (GA) has the capability of improving the forecasting performance of the ARIMA model by optimizing the ARIMA model parameters. The findings of this study revealed the high prediction accuracy of the proposed (GA-ARIMA) model. Moreover, it has provided better and consistent predictions compared to the traditional ARIMA model and can be a reliable method in predicting expected death rates as well as confirmed cases of COVID-19. Hence, it was concluded that combining ARIMA with GA is further accurate than ARIMA alone and GA can be an alternative to find the parameters and model orders for the ARIMA model.
{"title":"ARIMA Model Estimation Based on Genetic Algorithm for COVID-19 Mortality Rates","authors":"Mohanad A. Deif, A. Solyman, Rania E. Hammam","doi":"10.1142/s0219622021500528","DOIUrl":"https://doi.org/10.1142/s0219622021500528","url":null,"abstract":"This paper presents a forecasting model for the mortality rates of COVID-19 in six of the top most affected countries depending on the hybrid Genetic Algorithm and Autoregressive Integrated Moving Average (GA-ARIMA). It was aimed to develop an advanced and reliable predicting model that provides future forecasts of possible confirmed cases and mortality rates (Total Deaths per 1 million Population of COVID-19) that could help the public health authorities to develop plans required to resolve the crisis of the pandemic threat in a timely and efficient manner. The study focused on predicting the mortality rates of COVID-19 because the mortality rate determines the prevalence of highly contagious diseases. The Genetic algorithm (GA) has the capability of improving the forecasting performance of the ARIMA model by optimizing the ARIMA model parameters. The findings of this study revealed the high prediction accuracy of the proposed (GA-ARIMA) model. Moreover, it has provided better and consistent predictions compared to the traditional ARIMA model and can be a reliable method in predicting expected death rates as well as confirmed cases of COVID-19. Hence, it was concluded that combining ARIMA with GA is further accurate than ARIMA alone and GA can be an alternative to find the parameters and model orders for the ARIMA model.","PeriodicalId":13527,"journal":{"name":"Int. J. Inf. Technol. Decis. Mak.","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2021-08-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"80033043","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：