Soft Computing: Theory Innovations and Problem Solving Benefits

Permanent URI for this collection

Browse

Recent Submissions

Now showing 1 - 10 of 10
  • Item
    Smart Contract-based Consensus Building for Collaborative Medical Decision-Making
    ( 2022-01-04) Sellak, Hamza ; Baruwal Chhetri, Mohan ; Huang, Zijin ; Grobler, Marthie
    Medical decision-making is moving away from the traditional one-off dyadic encounter between the patient and physician, and transitioning towards a more inclusive, shared decision-making process that also considers the inputs from other stakeholders. This ensures that a patient's decision is not only based on a medical opinion, but also includes other considerations such as impact on family members, legal and financial implications, and experiences of patients in similar situations. However, given the sensitive nature of health data and decisions, there are several challenges associated with safeguarding the privacy, security and consent of all contributors and assuring the integrity of the process. We propose a collaborative medical decision-making platform that uses a consensus building mechanism implemented using Blockchain-based Smart Contracts to address some of the above challenges, thereby giving the participants confidence that both the decision-making process and the outcome(s) can be trusted. We also present a proof-of-concept implementation using the private Ethereum Blockchain to demonstrate practicability.
  • Item
    Review of Ultra Wide Band (UWB) for Indoor Positioning with application to the elderly
    ( 2022-01-04) Campaña Bastidas, Sixto ; Espinilla, Macarena ; Medina Quero, Javier
    The objective of this review is to analyze Ultra Wide Band (UWB) technology, as an option that allows developing new solutions in indoor positioning systems (IPS), mainly with a approach applied to the elderly. The methodology that has been applied corresponds to the definition of some basics concepts about UWB and some tests in the lab; the above to demonstrate the degree of accuracy that UWB offers compared to other technologies. The findings found and presented in this paper correspond to the identification of UWB as a technology with a high degree of accuracy for IPS; also, that there are other works related to the subject, with application in different areas, but specifically as an application for older people; regarding to the tests, these allowed to verify in the laboratory the operation and accuracy of UWB, for its possible application in IPS. The research described in this paper is the beginning of a implementation in a residence center, where accuracy in location and real-time response are important, in the future we hope make conclusive contributions of the implementations made.
  • Item
    On the Role of Context-Awareness in Binary Image Comparison
    ( 2022-01-04) Iglesias-Rey, Sara ; Castillo-Lopez, Aitor ; Lopez-Molina, Carlos ; De Baets, Bernard
    The quantification of image similarity has been a key topic in the computer vision literature for the past few years. Different mathematical theories have been used in the development of these measures, which we will refer to as comparison measures. An interesting aspect in the study of comparison measures is the natural requirement to replicate human behavior. In almost all cases, it is appropriate for a comparison measure to produce results that are consistent with how humans would perform that assessment. However, despite accepting this premise, most of the proposals in the literature ignore a fundamental characteristic of the way in which humans carry out this evaluation: the context of comparison. In this work we present a comparison measure for binary images that incorporates the context of comparison; more precisely, we introduce an approach for the generation of ultrametrics for the context-aware comparison of binary images.
  • Item
    Linear Hybrid Shrinkage of Weights for Forecast Selection and Combination
    ( 2022-01-04) Schulz, Felix ; Setzer, Thomas ; Balla, Nathalie
    Forecast combination is an established methodology to improve forecast accuracy. The primary questions in the current literature are how many and which forecasts to include (selection) and how to weight the selected forecasts (weighting). Although integrating both tasks seems appealing, we are only aware of a few data analytical models that integrate both tasks. We introduce Linear Hybrid Shrinkage (LHS), a novel method that uses information criteria from statistical learning theory to select forecasters and then shrinks the selection from their in-sample optimal weights linearly towards equality, while shrinking the non-selected forecasts towards zero. Simulation results show conditions (scenarios) where LHS leads to higher accuracy than LASSO-based Shrinkage, Linear Shrinkage of in-sample optimal weights, and a simple averaging of forecasts.
  • Item
    Distance Transformations Based on Ordered Weighted Averaging Operators
    ( 2022-01-04) Lopez-Molina, Carlos ; De Miguel, Laura ; Iglesias-Rey, Sara ; Bustince, Humberto ; De Baets, Bernard
    Binary image comparison has been a study subject for a long time, often rendering in context-specific solutions that depend upon the type of visual contents in the binary images. Distance transformations have been a recurrent tool in many of such solutions. The literature contains works on the generation and definition of distance transformations, but also on how to make a sensible use of their results. In this work, we attempt to solve one of the most critical problems in the application of distance transformations to real problems: their oversensitivity to certain spurious pixels which, even if having a minimal visual impact in the binary images to be compared, may have a severe impact on their distance transforms. With this aim, we combine distance transformations with Ordered Weighted Averaging (OWA) operators, a well-known information fusion tool from Fuzzy Set Theory.
  • Item
    Combinations of Affinity Functions for Different Community Detection Algorithms in Social Networks
    ( 2022-01-04) Fumanal Idocin, Javier ; Cordon, Oscar ; Minárová, María ; Alonso Betanzos, Amparo ; Bustince, Humberto
    Social network analysis is a popular discipline among the social and behavioural sciences, in which the relationships between different social entities are modelled as a network. One of the most popular problems in social network analysis is finding communities in its network structure. Usually, a community in a social network is a functional sub-partition of the graph. However, as the definition of community is somewhat imprecise, many algorithms have been proposed to solve this task, each of them focusing on different social characteristics of the actors and the communities. In this work we propose to use novel combinations of affinity functions, which are designed to capture different social mechanics in the network interactions. We use them to extend already existing community detection algorithms in order to combine the capacity of the affinity functions to model different social interactions than those exploited by the original algorithms.
  • Item
    Bayesian Augmentation of Deep Learning to Improve Video Classification
    ( 2022-01-04) Swize, Emmie ; Champagne, Lance ; Cox, Bruce ; Bihl, Trevor
    Traditional automated video classification methods lack measures of uncertainty, meaning the network is unable to identify those cases in which its predictions are made with significant uncertainty. This leads to misclassification, as the traditional network classifies each observation with same amount of certainty, no matter what the observation is. Bayesian neural networks are a remedy to this issue by leveraging Bayesian inference to construct uncertainty measures for each prediction. Because exact Bayesian inference is typically intractable due to the large number of parameters in a neural network, Bayesian inference is approximated by utilizing dropout in a convolutional neural network. This research compared a traditional video classification neural network to its Bayesian equivalent based on performance and capabilities. The Bayesian network achieves higher accuracy than a comparable non-Bayesian video network and it further provides uncertainty measures for each classification.
  • Item
    A Rule-Learning Approach for Detecting Faults in Highly Configurable Software Systems from Uniform Random Samples
    ( 2022-01-04) Heradio, Ruben ; Fernandez-Amoros, David ; Ruiz, Victoria ; Cobo, Manuel J.
    Software systems tend to become more and more configurable to satisfy the demands of their increasingly varied customers. Exhaustively testing the correctness of highly configurable software is infeasible in most cases because the space of possible configurations is typically colossal. This paper proposes addressing this challenge by (i) working with a representative sample of the configurations, i.e., a ``uniform'' random sample, and (ii) processing the results of testing the sample with a rule induction system that extracts the faults that cause the tests to fail. The paper (i) gives a concrete implementation of the approach, (ii) compares the performance of the rule learning algorithms AQ, CN2, LEM2, PART, and RIPPER, and (iii) provides empirical evidence supporting our procedure.
  • Item
    A Granular Computing-Based Model for Group Decision-Making in Multi-Criteria and Heterogeneous Environments
    ( 2022-01-04) Cabrerizo, Francisco ; González-Quesada, Juan Carlos ; Pérez, Ignacio ; Herrera-Viedma, Enrique
    Granular computing is a growing computing paradigm of information processing that covers any techniques, methodologies, and theories employing information granules in complex problem solving. Within the recent past, it has been applied to solve group decision-making processes and different granular computing-based models have been constructed, which focus on some particular aspects of these decision-making processes. This study presents a new granular computing-based model for group decision-making processes defined in multi-criteria and heterogeneous environments that is able to improve with minimum adjustment both the consistency associated with individual decision-makers and the consensus related to the group. Unlike the existing granular computing-based approaches, this new one is able to take into account a higher number of features when dealing with this kind of decision-making processes.
  • Item
    Introduction to the Minitrack on Soft Computing: Theory Innovations and Problem Solving Benefits
    ( 2022-01-04) Herrera-Viedma, Enrique ; Cabrerizo, Francisco ; Pérez, Ignacio