In today’s world different data sets are available on which regression or classification algorithms of machine learning are applied. One of the classification algorithms is k-nearest neighbor (kNN) which computes distance amongst various rows in a dataset. The performance of kNN is evaluated based on K-value and distance metric used, where K is the total count of neighboring elements. Many different distance metrics have been used by researchers in literature, one of them is Canberra distance metric. In this paper the performance of kNN based on Canberra distance metric is measured on different datasets, further the proposed Canberra distance metric, namely, Modified Euclidean-Canberra Blend Distance (MECBD) metric has been applied to the kNN algorithm which led to improvement of class prediction efficiency on the same datasets measured in terms of accuracy, precision, recall, F1-score for different values of k. Further, this study depicts that MECBD metric use led to improvement in accuracy value 80.4% to 90.3%, 80.6% to 85.4% and 70.0% to 77.0% for various data sets used. Also, implementation of ROC curves and auc for k= 5 is done to show the improvement is kNN model prediction which showed increase in auc values for different data sets, for instance increase in auc values from 0.873 to 0.958 for Spine (2 Classes) dataset, 0.857 to 0.940, 0.983 to 0.983 (no change), 0.910 to 0.957 for DH, SL and NO class for Spine (3 Classes) data set and 0.651 to 0.742 for Haberman’s data set.
{"title":"Modified Euclidean-Canberra blend distance metric for kNN classifier","authors":"Gaurav Sandhu, Amandeep Singh, Puneet Singh Lamba, Deepali Virmani, Gopal Chaudhary","doi":"10.3233/idt-220233","DOIUrl":"https://doi.org/10.3233/idt-220233","url":null,"abstract":"In today’s world different data sets are available on which regression or classification algorithms of machine learning are applied. One of the classification algorithms is k-nearest neighbor (kNN) which computes distance amongst various rows in a dataset. The performance of kNN is evaluated based on K-value and distance metric used, where K is the total count of neighboring elements. Many different distance metrics have been used by researchers in literature, one of them is Canberra distance metric. In this paper the performance of kNN based on Canberra distance metric is measured on different datasets, further the proposed Canberra distance metric, namely, Modified Euclidean-Canberra Blend Distance (MECBD) metric has been applied to the kNN algorithm which led to improvement of class prediction efficiency on the same datasets measured in terms of accuracy, precision, recall, F1-score for different values of k. Further, this study depicts that MECBD metric use led to improvement in accuracy value 80.4% to 90.3%, 80.6% to 85.4% and 70.0% to 77.0% for various data sets used. Also, implementation of ROC curves and auc for k= 5 is done to show the improvement is kNN model prediction which showed increase in auc values for different data sets, for instance increase in auc values from 0.873 to 0.958 for Spine (2 Classes) dataset, 0.857 to 0.940, 0.983 to 0.983 (no change), 0.910 to 0.957 for DH, SL and NO class for Spine (3 Classes) data set and 0.651 to 0.742 for Haberman’s data set.","PeriodicalId":43932,"journal":{"name":"Intelligent Decision Technologies-Netherlands","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-05-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135140458","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}
Facial emotion recognition analysis is widely used in various social fields, including Law Enforcement for police interrogation, virtual assistants, hospitals for understanding patients’ expressions, etc. In the field of medical treatment such as psychologically affected patients, patients undergoing difficult surgeries, etc require emotional recognition in real-time. The current emotional analysis employs interest points as landmarks in facial images affected by a few emotions Many researchers have proposed 7 different types of emotions (amusement, anger, disgust, fear, and sadness). In our work, we propose a deep learning-based multi-level graded facial emotions of 21 different types with our proposed facial emotional feature extraction technique called as Deep Facial Action Extraction Units (DFAEU). Then using our Multi-Class Artificial Neural Network (MCANN) architecture the model is trained to classify different emotions. The proposed method makes use of VGG-16 for the analysis of emotion grades. The performance of our model is evaluated using two algorithms Sparse Batch Normalization CNN (SBN-CNN) and CNN with Attention mechanism (ACNN) along with datasets Facial Emotion Recognition Challenge (FERC-2013). Our model outperforms 86.34 percent and 98.6 percent precision.
{"title":"Multi-level graded facial emotion intensity recognition using MCANN for health care","authors":"Nazmin Begum, A. Syed Mustafa","doi":"10.3233/idt-220301","DOIUrl":"https://doi.org/10.3233/idt-220301","url":null,"abstract":"Facial emotion recognition analysis is widely used in various social fields, including Law Enforcement for police interrogation, virtual assistants, hospitals for understanding patients’ expressions, etc. In the field of medical treatment such as psychologically affected patients, patients undergoing difficult surgeries, etc require emotional recognition in real-time. The current emotional analysis employs interest points as landmarks in facial images affected by a few emotions Many researchers have proposed 7 different types of emotions (amusement, anger, disgust, fear, and sadness). In our work, we propose a deep learning-based multi-level graded facial emotions of 21 different types with our proposed facial emotional feature extraction technique called as Deep Facial Action Extraction Units (DFAEU). Then using our Multi-Class Artificial Neural Network (MCANN) architecture the model is trained to classify different emotions. The proposed method makes use of VGG-16 for the analysis of emotion grades. The performance of our model is evaluated using two algorithms Sparse Batch Normalization CNN (SBN-CNN) and CNN with Attention mechanism (ACNN) along with datasets Facial Emotion Recognition Challenge (FERC-2013). Our model outperforms 86.34 percent and 98.6 percent precision.","PeriodicalId":43932,"journal":{"name":"Intelligent Decision Technologies-Netherlands","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-05-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"136215667","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}
The Sustainable Development Goals (SDGs) initiative by corporations requires that their business activities be linked to the 17 SDGs. Moreover, the digital transformation (DX) of enterprises requires the use of digital technology to realize a digital company with competitive advantage. It is inefficient to implement the SDGs and DX initiatives separately in an enterprise. In this paper, we propose a solution to the question, “How do we combine knowledge for the SDGs and DX?”
{"title":"Digital SDGs framework towards knowledge integration","authors":"Shuichiro Yamamoto","doi":"10.3233/idt-220276","DOIUrl":"https://doi.org/10.3233/idt-220276","url":null,"abstract":"The Sustainable Development Goals (SDGs) initiative by corporations requires that their business activities be linked to the 17 SDGs. Moreover, the digital transformation (DX) of enterprises requires the use of digital technology to realize a digital company with competitive advantage. It is inefficient to implement the SDGs and DX initiatives separately in an enterprise. In this paper, we propose a solution to the question, “How do we combine knowledge for the SDGs and DX?”","PeriodicalId":43932,"journal":{"name":"Intelligent Decision Technologies-Netherlands","volume":null,"pages":null},"PeriodicalIF":1.0,"publicationDate":"2022-11-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"46221827","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 modern engineering, science and technological problems inevitably faces problems of uncertainty in various aspects such as natural disaster, chaotic decision making, human resource availability, processing capability and constraints and limitations imposed by the authority. This problem has to be solved by a methodology which takes care of such uncertain information. As the analyst solves this problem, the decision maker and the implementer have to coordinate with the analyst for taking up a decision on a successful strategic and holistic decision making for final implementation. Such a complex problems in an imperfect world can be solved by the robust and flexible optimization methodologies. The objective of the special issue is to enlighten the researchers working on the development of innovative and novel techniques and methodologies to improve the performance of current development on the advanced algorithms related real world practical problems in the research areas of novel and modern optimization and its application in Engineering, Science and Technology. The special issue includes ten outstanding research papers in the field of optimization and its application in engineering and technology. The editors sincerely thank the referees’ and the authors’ for their marvelous contributing in making this special issue a successful publication. This special issue will contribute new body of the knowledge to the researchers across the planet.
{"title":"Special Issue On: Optimization for Engineering, Science and Technology","authors":"P. Vasant, J. Watada","doi":"10.3233/IDT-160272","DOIUrl":"https://doi.org/10.3233/IDT-160272","url":null,"abstract":"Many modern engineering, science and technological problems inevitably faces problems of uncertainty in various aspects such as natural disaster, chaotic decision making, human resource availability, processing capability and constraints and limitations imposed by the authority. This problem has to be solved by a methodology which takes care of such uncertain information. As the analyst solves this problem, the decision maker and the implementer have to coordinate with the analyst for taking up a decision on a successful strategic and holistic decision making for final implementation. Such a complex problems in an imperfect world can be solved by the robust and flexible optimization methodologies. The objective of the special issue is to enlighten the researchers working on the development of innovative and novel techniques and methodologies to improve the performance of current development on the advanced algorithms related real world practical problems in the research areas of novel and modern optimization and its application in Engineering, Science and Technology. The special issue includes ten outstanding research papers in the field of optimization and its application in engineering and technology. The editors sincerely thank the referees’ and the authors’ for their marvelous contributing in making this special issue a successful publication. This special issue will contribute new body of the knowledge to the researchers across the planet.","PeriodicalId":43932,"journal":{"name":"Intelligent Decision Technologies-Netherlands","volume":null,"pages":null},"PeriodicalIF":1.0,"publicationDate":"2017-04-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"77885950","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}
Estimation by Analogy is a popular method in the field of software cost estimation. However, the configuration of the method affects estimation accuracy, which has a great effect on project managem...
{"title":"A genetic algorithm approach to global optimization of software cost estimation by analogy","authors":"MiliosDimitrios, StamelosIoannis, ChatzibagiasChristos","doi":"10.5555/2608538.2608543","DOIUrl":"https://doi.org/10.5555/2608538.2608543","url":null,"abstract":"Estimation by Analogy is a popular method in the field of software cost estimation. However, the configuration of the method affects estimation accuracy, which has a great effect on project managem...","PeriodicalId":43932,"journal":{"name":"Intelligent Decision Technologies-Netherlands","volume":null,"pages":null},"PeriodicalIF":1.0,"publicationDate":"2013-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"83834011","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 : 2012-05-01DOI: 10.1007/978-3-642-29977-3_24
Chia-Yu Hsu, Chen-Fu Chien, Ya-Chun Lai
{"title":"Main Branch Decision Tree Algorithm for Yield Enhancement with Class Imbalance","authors":"Chia-Yu Hsu, Chen-Fu Chien, Ya-Chun Lai","doi":"10.1007/978-3-642-29977-3_24","DOIUrl":"https://doi.org/10.1007/978-3-642-29977-3_24","url":null,"abstract":"","PeriodicalId":43932,"journal":{"name":"Intelligent Decision Technologies-Netherlands","volume":null,"pages":null},"PeriodicalIF":1.0,"publicationDate":"2012-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"87541982","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 : 2012-05-01DOI: 10.1007/978-3-642-29920-9_6
Chen-Fu Chien, Chia-Yu Hsu, Sheng-Chiao Lin
{"title":"Manufacturing Intelligence to Forecast the Customer Order Behavior for Vendor Managed Inventory","authors":"Chen-Fu Chien, Chia-Yu Hsu, Sheng-Chiao Lin","doi":"10.1007/978-3-642-29920-9_6","DOIUrl":"https://doi.org/10.1007/978-3-642-29920-9_6","url":null,"abstract":"","PeriodicalId":43932,"journal":{"name":"Intelligent Decision Technologies-Netherlands","volume":null,"pages":null},"PeriodicalIF":1.0,"publicationDate":"2012-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"85419612","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}
Leonardo Garrido, F. Cervantes-Pérez, Cleotilde González, M. Mora
An ongoing and main challenge for intelligent decision technologies is the need to support knowledgeintensive tasks that usually are surging in multiple domains of applications such as manufacture [13], finance and insurance [10], and generic knowledge-based service business [12]. Engineering and management systems have relied on knowledge generated from several related areas including Decision Support Systems, Artificial Intelligence and Operations Research. Most recently, in the last decade, a business management perspective realized through Knowledge Management (KM) approach has been incorporated to this research stream driven by a knowledge-based services economy [9,11]. Thus, a new type of IT system called Knowledge Management System (KMS) [2] has emerged to leverage “professional and managerial activities by focusing on creating, gathering, organizing, and disseminating an organization’s “knowledge” as opposed to “information” or “data” (idem, p. 1). While KMS are engineered and managed by using multiple IT, we consider relevant the development of KMS based on intelligent decision technologies and the enhancement of the decision-making process [6]. Through following the seminal directions [7,8] established by the eminent AI scientists Herbert A. Simon (1916–2001) and Alan Newell (1927–1992), and the system’s emergent property established by the Theory of Systems [1,4], we support also the notion of a “distinct computer systems level, lying immediately above the symbol level, which is characterized by knowledge as the medium and the principle of rationality as the law of behavior” (Newell, p. 7) as a core conceptualization for the realization of such KMS. We believe that the five invited and peer-reviewed research papers in this special issue in “Engineering and Management of IDTs for Knowledge Management Systems”, advance our scientific knowledge on the state of the art of intelligent knowledge management systems in a context of decision-making process. One research paper reports an improved algorithm for an automatic joint of knowledge stored via ontologies. Three another research papers analyze deeply the KMS support challenges and the KMS emergent simulation-based design architectures and paradigms. Finally, a fifth paper, reviews the state of the art of KMS focused on the particular problem of improving the utilization of standards and models of process in the context of software and systems engineering. In first paper, titled “Automatic Fusion of knowledge stored in Ontologies”, Dr. Alma-Delia Cueva and Professor Adolfo Guzmán-Arenas (Computer Research Center, Instituto Politecnico Nacional, México), investigate the knowledge fusion problem which is a seamless process in human beings. However, for an automated system, authors report that algorithms of ontologies fusion lack of critical features such as the processing of synonyms, homonyms, redundancies, apparent contradictions, and inconsistencies. Authors, consequently presents a new
智能决策技术面临的一个持续和主要挑战是需要支持知识密集型任务，这些任务通常在多个应用领域激增，如制造业[13]、金融和保险[10]以及通用知识服务业务[12]。工程和管理系统依赖于几个相关领域产生的知识，包括决策支持系统、人工智能和运筹学。最近，在过去十年中，通过知识管理(KM)方法实现的企业管理视角已被纳入以知识为基础的服务经济驱动的研究流中[9,11]。因此，一种名为知识管理系统(KMS)的新型IT系统[2]已经出现，它通过专注于创造、收集、组织和传播组织的“知识”(而不是“信息”或“数据”)来利用“专业和管理活动”(idem，第1页)。虽然KMS是通过使用多个IT来设计和管理的，但我们认为基于智能决策技术和决策过程增强的KMS的发展是相关的[6]。通过遵循杰出的人工智能科学家Herbert a . Simon(1916-2001)和Alan Newell(1927-1992)建立的开创性方向[7,8]，以及系统理论(Theory of Systems)建立的系统涌现特性[1,4]，我们也支持“独特的计算机系统级别，位于符号级别之上，其特征是知识作为媒介，理性原则作为行为法则”的概念(Newell，第7页)作为实现这种知识管理系统的核心概念。我们相信，本期《知识管理系统IDTs的工程与管理》特刊上的五篇特邀和同行评审的研究论文，推动了我们对决策过程中智能知识管理系统现状的科学认识。一篇研究论文报道了一种通过本体存储的知识自动连接的改进算法。另外三篇研究论文深入分析了KMS支持挑战和基于KMS紧急仿真的设计体系结构和范式。最后，第五篇论文回顾了KMS的现状，重点关注了在软件和系统工程的背景下提高过程的标准和模型的使用的特殊问题。在第一篇题为“存储在本体中的知识的自动融合”的论文中，Alma-Delia Cueva博士和Adolfo教授Guzmán-Arenas(国立理工学院计算机研究中心，m xico)研究了人类无缝过程中的知识融合问题。然而，对于自动化系统，作者报告了本体融合算法缺乏关键特征，如同义词、同义词、冗余、明显矛盾和不一致的处理。因此，作者提出了一种新的本体合并(OM)方法，其算法和实现以自动方式(无需人工干预)连接两个本体(从Web文档中获得)，产生第三个本体，并考虑到上述问题，交付结果接近于人类的性能。本文为智能KMS的设计提供了一种新的方法和算法。在第二篇论文中，题为“挑战计算机软件前沿和人类对
{"title":"Guest-editorial: Special issue title on engineering and management of IDTs for knowledge management systems","authors":"Leonardo Garrido, F. Cervantes-Pérez, Cleotilde González, M. Mora","doi":"10.3233/IDT-2010-0065","DOIUrl":"https://doi.org/10.3233/IDT-2010-0065","url":null,"abstract":"An ongoing and main challenge for intelligent decision technologies is the need to support knowledgeintensive tasks that usually are surging in multiple domains of applications such as manufacture [13], finance and insurance [10], and generic knowledge-based service business [12]. Engineering and management systems have relied on knowledge generated from several related areas including Decision Support Systems, Artificial Intelligence and Operations Research. Most recently, in the last decade, a business management perspective realized through Knowledge Management (KM) approach has been incorporated to this research stream driven by a knowledge-based services economy [9,11]. Thus, a new type of IT system called Knowledge Management System (KMS) [2] has emerged to leverage “professional and managerial activities by focusing on creating, gathering, organizing, and disseminating an organization’s “knowledge” as opposed to “information” or “data” (idem, p. 1). While KMS are engineered and managed by using multiple IT, we consider relevant the development of KMS based on intelligent decision technologies and the enhancement of the decision-making process [6]. Through following the seminal directions [7,8] established by the eminent AI scientists Herbert A. Simon (1916–2001) and Alan Newell (1927–1992), and the system’s emergent property established by the Theory of Systems [1,4], we support also the notion of a “distinct computer systems level, lying immediately above the symbol level, which is characterized by knowledge as the medium and the principle of rationality as the law of behavior” (Newell, p. 7) as a core conceptualization for the realization of such KMS. We believe that the five invited and peer-reviewed research papers in this special issue in “Engineering and Management of IDTs for Knowledge Management Systems”, advance our scientific knowledge on the state of the art of intelligent knowledge management systems in a context of decision-making process. One research paper reports an improved algorithm for an automatic joint of knowledge stored via ontologies. Three another research papers analyze deeply the KMS support challenges and the KMS emergent simulation-based design architectures and paradigms. Finally, a fifth paper, reviews the state of the art of KMS focused on the particular problem of improving the utilization of standards and models of process in the context of software and systems engineering. In first paper, titled “Automatic Fusion of knowledge stored in Ontologies”, Dr. Alma-Delia Cueva and Professor Adolfo Guzmán-Arenas (Computer Research Center, Instituto Politecnico Nacional, México), investigate the knowledge fusion problem which is a seamless process in human beings. However, for an automated system, authors report that algorithms of ontologies fusion lack of critical features such as the processing of synonyms, homonyms, redundancies, apparent contradictions, and inconsistencies. Authors, consequently presents a new ","PeriodicalId":43932,"journal":{"name":"Intelligent Decision Technologies-Netherlands","volume":null,"pages":null},"PeriodicalIF":1.0,"publicationDate":"2010-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"90866493","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：