Big Data and Web Intelligence

2015 ◽  
pp. 190-207 ◽  
Author(s):  
Alberto Pliego ◽  
Fausto Pedro García Márquez
Keyword(s):  
Decision Making ◽  
Decision Trees ◽  
Computational Cost ◽  
New Approach ◽  
Computational Costs ◽  
Use Of Data ◽  
Decision Making Processes ◽  
Complex Decision Making ◽  
Unique Factor ◽  
Complex Decision

The growing amount of available data generates complex problems when they need to be treated. Usually these data come from different sources and inform about different issues, however, in many occasions these data can be interrelated in order to gather strategic information that is useful for Decision Making processes in multitude of business. For a qualitatively and quantitatively analysis of a complex Decision Making process is critical to employ a correct method due to the large number of operations required. With this purpose, this chapter presents an approach employing Binary Decision Diagram applied to the Logical Decision Tree. It allows addressing a Main Problem by establishing different causes, called Basic Causes and their interrelations. The cases that have a large number of Basic Causes generate important computational costs because it is a NP-hard type problem. Moreover, this chapter presents a new approach in order to analyze big Logical Decision Trees. However, the size of the Logical Decision Trees is not the unique factor that affects to the computational cost but the procedure of resolution can widely vary this cost (ordination of Basic Causes, number of AND/OR gates, etc.) A new approach to reduce the complexity of the problem is hereby presented. It makes use of data derived from simpler problems that requires less computational costs for obtaining a good solution. An exact solution is not provided by this method but the approximations achieved have a low deviation from the exact.

Big Data and Web Intelligence

Big Data ◽  
2016 ◽  
pp. 229-246 ◽  
Author(s):  
Alberto Pliego ◽  
Fausto Pedro García Márquez
Keyword(s):  
Decision Making ◽  
Decision Trees ◽  
Computational Cost ◽  
New Approach ◽  
Computational Costs ◽  
Use Of Data ◽  
Decision Making Processes ◽  
Complex Decision Making ◽  
Unique Factor ◽  
Complex Decision

The growing amount of available data generates complex problems when they need to be treated. Usually these data come from different sources and inform about different issues, however, in many occasions these data can be interrelated in order to gather strategic information that is useful for Decision Making processes in multitude of business. For a qualitatively and quantitatively analysis of a complex Decision Making process is critical to employ a correct method due to the large number of operations required. With this purpose, this chapter presents an approach employing Binary Decision Diagram applied to the Logical Decision Tree. It allows addressing a Main Problem by establishing different causes, called Basic Causes and their interrelations. The cases that have a large number of Basic Causes generate important computational costs because it is a NP-hard type problem. Moreover, this chapter presents a new approach in order to analyze big Logical Decision Trees. However, the size of the Logical Decision Trees is not the unique factor that affects to the computational cost but the procedure of resolution can widely vary this cost (ordination of Basic Causes, number of AND/OR gates, etc.) A new approach to reduce the complexity of the problem is hereby presented. It makes use of data derived from simpler problems that requires less computational costs for obtaining a good solution. An exact solution is not provided by this method but the approximations achieved have a low deviation from the exact.

scholarly journals ЭФФЕКТИВНОСТЬ МЕТОДОВ ОПРЕДЕЛЕНИЯ ГРУППОВЫХ СИСТЕМ ПРЕДПОЧТЕНИЙ ДИСПЕТЧЕРОВ НА ОПАСНОСТИ ХАРАКТЕРНЫХ ОШИБОК, СОВЕРШАЕМЫХ В ПРОЦЕССЕ УПРАВЛЕНИЯ ВОЗДУШНЫМ ДВИЖЕНИЕМ

2018 ◽  
pp. 93-103
Author(s):  
Алексей Николаевич Рева ◽  
Шахин Шахвели-оглы Насиров ◽  
Бала Мушгюль-оглы Мирзоев
Keyword(s):  
Decision Making ◽  
Parametric Optimization ◽  
Professional Activity ◽  
Air Traffic Controllers ◽  
Main Emphasis ◽  
Decision Making Processes ◽  
Complex Decision Making ◽  
Coefficient Of Concordance ◽  
Complex Decision ◽  
Non Parametric

The human factor problem should be solved by identifying, qualifying and preventing the erroneous actions of the air traffic controllers. It is presented two schemes explaining the structure of human qualimetry factor and the interaction of the components of the ICAO safety concept, where the main emphasis is on an aviation personnel’ attitude to dangerous actions or conditions, which is revealed by the qualimetry of the decision-making processes’ characteristics: the attitude towards risk (the main dominants and fuzzy assessments), levels of claims, dangerous qualities and preferences systems. The preferences systems are considered as ordered characteristics and indicators of professional activity, which are subjectively compared with the positions of influence on flight safety. The spectrum of n = 21 characteristic errors was formed considering the recommendations of ICAO, EUROCONTROL and accident statistics. It is determined that procedures of collecting the information of errors danger contribute their recognition, memorization, and avoidance: controllers who passed the test according to the proposed method before training made by one third fewer errors in its process. Two criteria for assessing group preferences are realized: the level of consensus (known as Kendall’s coefficient of concordance) and the severity of the ranking, determined by the presence of "related" ranks, for which a special indicator is introduced. It is defined that this indicator should be determined both for the sample of respondents and for the preferences group systems of developed with the chosen method of individual opinions’ aggregation. It was performed the comparative analysis of complex decision-making strategies of effectiveness in the construction of a preferences group systems m = 65 controllers: sum and averaging of ranks, classical criteria (Wald's, Savage's and Laplace's criterion), optimal prediction, applying the non-parametric optimization of the preferences group systems. The non-parametric optimization of the group system of pre-readings was carried out by Kemeny median and it was proved that it was the closest to all the results obtained by other methods and strategies

Decision Making Approaches for Advanced Manufacturing Technology Evaluation and Selection

2012 ◽  
pp. 403-438 ◽  
Author(s):  
Aidé Maldonado-Macías ◽  
Jorge Luis García-Alcaraz ◽  
Francisco Javier Marrodan Esparza ◽  
Carlos Alberto Ochoa Ortiz Zezzatti
Keyword(s):  
Decision Making ◽  
Manufacturing Technology ◽  
Advanced Manufacturing Technology ◽  
Advanced Manufacturing ◽  
Manufacturing Companies ◽  
Decision Making Processes ◽  
Complex Decision Making ◽  
Broad Variety ◽  
Complex Decision ◽  
Selection Of

Advanced Manufacturing Technology (AMT) constitutes one of the most important resources of manufacturing companies to achieve success in an extremely competitive world. Decision making processes for the Evaluation and Selection of AMT in these companies must lead to the best alternative available. Industry is looking for a combination of flexibility and high quality by doing significant investments in AMT. The proliferation of this technology has generated a whole field of knowledge related to the design, evaluation and management of AMT systems which includes a broad variety of methodologies and applications. This chapter presents a theoretical review of the term AMT, its diverse classification and a collection of the most effective multi-attribute models and methodologies available to support these processes. Relevant advantages are found in these models since they can manage complex decision making problems which involve large amount of information and attributes. These attributes frequently can be tangible and intangible when vagueness and uncertainty exist. There are several multi-attribute methodologies which are extensively known and used in literature; nevertheless, a new fuzzy multi-attribute axiomatic design approach is explained for an ergonomic compatibility evaluation of AMT.

scholarly journals In the Era of Digitalising Shop Floor Management: In Blissful Ignorance of Superfluous Work

2020 ◽  
Author(s):  
John Bang Mathiasen ◽  
Henning de Haas
Keyword(s):  
Decision Making ◽  
Knowledge Sharing ◽  
Reflective Thinking ◽  
Abductive Reasoning ◽  
Smart Manufacturing ◽  
Shop Floor ◽  
Decision Making Processes ◽  
Complex Decision Making ◽  
Complex Decision

This study aims to understand the extent of superfluous work at shop floors and suggests some managerial opportunities for reducing superfluous work. Drawing on the abductive reasoning, the research systematically combines a theoretical conceptualisation of decision-making processes in a digitalised manufacturing with an empirical enquiry of a smart manufacturing. The paper reveals superfluous work if decision-making processes cross disciplinary and/or organisational boundaries. Superfluous work occurs because of lacking data and information to guide reflective thinking and knowledge sharing. In relation to high complex decision making the ongoing implementation of workarounds does also cause superfluous work. Prerequisites for reducing superfluous work are accessibility of applicable data to guide reflective thinking and knowledge sharing.

scholarly journals Decision-making on Implementation of IPO Under Topological Uncertainty

2015 ◽  
Vol 63 (1) ◽  
pp. 193-200 ◽  
Author(s):  
Karel Doubravský ◽  
Tomáš Meluzín ◽  
Mirko Dohnal
Keyword(s):  
Decision Making ◽  
Decision Trees ◽  
Initial Public Offering ◽  
Decision Makers ◽  
Structure Topology ◽  
Complex Decision Making ◽  
Flexible Integration ◽  
Complex Decision ◽  
Public Offering

IPO (Initial Public Offering) is a complex decision making task which is always associated with different types of uncertainty. Poor accuracies of available probabilities of lotteries e.g. quantification of investor interest is studied in the first part of this paper (Meluzín, Doubravský, Dohnal, 2012). However, IPO is often prohibitively ill-known. This paper takes into consideration the fact that decision makers cannot specify the structure/topology of the relevant decision tree. It means that one IPO task is specified by several (partially) different decision trees which comes from different sources e.g. from different teams of decision makers/experts. A flexible integration of those trees is based on fuzzy logic using the reconciliation (Meluzín, Doubravský, Dohnal, 2012). The developed algorithm is demonstrated by a case study which is presented in details. The IPO case integrates two partially different decision trees.

To Cross or Not To Cross

2013 ◽  
Vol 27 (3) ◽  
pp. 113-123 ◽  
Author(s):  
Evelien Kostermans ◽  
Renske Spijkerman ◽  
Rutger C. M. E. Engels ◽  
Harold Bekkering ◽  
Ellen R. A. de Bruijn
Keyword(s):  
Decision Making ◽  
Event Related Potential ◽  
Anterior Cingulate ◽  
Specific Response ◽  
Conflict Monitoring ◽  
Traffic Light ◽  
Decision Making Processes ◽  
Complex Decision Making ◽  
Complex Decision ◽  
Everyday Knowledge

Different theoretical accounts have attempted to integrate anterior cingulate cortex involvement in relation to conflict detection, error-likelihood predictions, and error monitoring. Regarding the latter, event-related potential studies have identified the feedback-related negativity (FRN) component in relation to processing feedback which indicates that a particular outcome was worse than expected. According to the conflict-monitoring theory the stimulus-locked N2 reflects pre-response conflict. Assumptions of these theories have been made on the basis of relatively simple response-mapping tasks, rather than more complex decision-making processes associated with everyday situations. The question remains whether expectancies and conflicts induced by everyday knowledge similarly affect decision-making processes. To answer this question, electroencephalogram and behavioral measurements were obtained while participants performed a simulated traffic task that varied high and low ambiguous situations at an intersection by presenting multiple varying traffic light combinations. Although feedback was kept constant for the different conditions, the tendency to cross was more pronounced for traffic light combinations that in reallife are associated with proceeding, as opposed to more ambiguous traffic light combinations not uniquely associated with a specific response. On a neurophysiological level, the stimulus-locked N2 was enhanced on trials that induced experience-based conflict and the FRN was more pronounced for negative as compared to positive feedback, but did not differ as a function of everyday expectancies related to traffic rules. The current study shows that well-learned everyday rules may influence decision-making processes in situations that are associated with the application of these rules, even if responding accordingly does not lead to the intended outcomes.

A Mashup Application to Support Complex Decision Making for Retail Consumers

2012 ◽  
pp. 277-294 ◽  
Author(s):  
Steven Walczak ◽  
Deborah L. Kellogg ◽  
Dawn G. Gregg
Keyword(s):  
Decision Making ◽  
Information Overload ◽  
Decision Quality ◽  
Online Tools ◽  
Decision Making Processes ◽  
Complex Decision Making ◽  
Complex Decision ◽  
Time Required ◽  
Decision Complexity

Purchase processes often require complex decision making and consumers frequently use Web information sources to support these decisions. However, increasing amounts of information can make finding appropriate information problematic. This information overload, coupled with decision complexity, can increase time required to make a decision and reduce decision quality. This creates a need for tools that support these decision-making processes. Online tools that bring together data and partial solutions are one option to improve decision making in complex, multi-criteria environments. An experiment using a prototype mashup application indicates that these types of applications may significantly decrease time spent and improve overall quality of complex retail decisions.

Online Role-Based Learning Designs for Teaching Complex Decision Making

2011 ◽  
pp. 295-311
Author(s):  
Robert McLaughlan ◽  
Denise Kirkpatrick
Keyword(s):  
Decision Making ◽  
Learning Design ◽  
Effective Learning ◽  
Decision Context ◽  
Value Judgements ◽  
Information And Communication ◽  
Decision Making Processes ◽  
Complex Decision Making ◽  
Complex Decision ◽  
Role Based

Decision-making processes in relation to complex natural resources require recognition and accommodation of diverse and competing perspectives in a decision context that is frequently ill defined and fraught with value judgements. Online environments can be used to develop students’ skills and understanding of these issues. The focus of this chapter is the learning design of an online roleplay-simulation (Mekong e-Sim) which was created to develop learning experiences about these types of issues across multiple institutions with students from the disciplines of engineering and the humanities. The key stages of interaction within the e-Sim are described and linked to student tasks, resources, and supports. The evolution and adaptation of the learning design used in the Mekong e-Sim has been described. Eight key challenges in the design and implementation of online roleplay-simulations have been identified. In this chapter, we have tried to address a gap in the online role-based collaborative learning literature about the design of these activities, linkages between pedagogy and information and communication technology, and how to exploit these linkages for effective learning.

Sign in / Sign up

Export Citation Format

Share Document