AI Article Synopsis

  • The paper presents a new method for creating and analyzing granular input spaces in numeric models by assigning varying levels of information granularity to input variables, enhancing understanding of their precision.
  • This approach results in outputs that also consist of information granules like intervals or fuzzy sets, maximizing the specificity and coverage of the granular model.
  • The optimization process utilizes differential evolution to balance the specificity of model results with the breadth of data coverage, assessed through experimental studies using both synthetic datasets and real data from machine learning sources.

Article Abstract

In this paper, we elaborate on a new design approach to the development and analysis of granular input spaces and ensuing granular modeling. Given a numeric model (no matter what specific design methodology has been used to construct it and what architecture has been adopted), we form a granular input space through allocating a certain level of information granularity across the input variables. The formation of granular input space helps us gain a better insight into the ranking of input variables with respect to their precision (the variables with a lower level of information granularity need to be specified in a precise way when estimating the inputs). As a consequence, for granular inputs, the outputs of the granular model are also information granules (say, intervals, fuzzy sets, rough sets, etc.). It is shown that the process of forming granular input space can be sought as an optimization of allocation of information granularity across the input variables so that the specificity of the corresponding granular outputs of the granular model becomes the highest while coverage of data becomes maximized. The construction of granular input space dwells upon two fundamental principles of granular computing-the principle of justifiable granularity and the optimal allocation of information granularity. The quality of the granular input space is quantified in terms of the two conflicting criteria, that is, the specificity of the results produced by the granular model and the coverage of experimental data delivered by this model. In the ensuing optimization problem, one maximizes a product of specificity and coverage. Differential evolution is engaged in this optimization task. The experimental studies involve both synthetic dataset and data coming from the machine learning repository.

Download full-text PDF

Source
http://dx.doi.org/10.1109/TCYB.2019.2899633DOI Listing

Publication Analysis

Top Keywords

granular input
28
input space
24
granular
13
input variables
12
granular model
12
input
10
level granularity
8
granularity input
8
outputs granular
8
allocation granularity
8

Similar Publications

Interpretable Deep-Learning p Prediction for Small Molecule Drugs via Atomic Sensitivity Analysis.

J Chem Inf Model

January 2025

Department of Chemical and Physical Biology, Vanderbilt University, Nashville, Tennessee 37232, United States.

Machine learning (ML) models now play a crucial role in predicting properties essential to drug development, such as a drug's logscale acid-dissociation constant (p). Despite recent architectural advances, these models often generalize poorly to novel compounds due to a scarcity of ground-truth data. Further, these models lack interpretability.

View Article and Find Full Text PDF

Introduction: A fundamental property of the neocortex is its columnar organization in many species. Generally, neurons of the same column share stimulus preferences and have strong anatomical connections across layers. These features suggest that neurons within a column operate as one unified network.

View Article and Find Full Text PDF

Background: Health economic evaluations require cost data as a key input, and reimbursement policies and systems should incentivize valuable care. Subfertility is a growing global phenomenon, and Dutch per-treatment DRGs alone do not support value-based decision-making because they don't reflect patient-level variation or the impact of technologies on costs across entire patient pathways.

Methods: We present a real-world micro-costing analysis of subfertility patient pathways (n = 4.

View Article and Find Full Text PDF

Under natural conditions, animals repeatedly encounter the same visual scenes, objects or patterns repeatedly. These repetitions constitute statistical regularities, which the brain captures in an internal model through learning. A signature of such learning in primate visual areas V1 and V4 is the gradual strengthening of gamma synchronization.

View Article and Find Full Text PDF

Aims: Nirmatrelvir/ritonavir (NMV/r) is an orally administered antiviral indicated for the outpatient treatment of adult patients with mild-to-moderate COVID-19 at high risk for disease progression to severe illness. We estimated the cost-effectiveness of NMV/r versus best supportive care for 54 patient cohorts, specified according to age, vaccination status and comorbidity burden.

Materials And Methods: A previously published and validated cost-effectiveness model was utilized and adapted to the Swedish setting.

View Article and Find Full Text PDF

Want AI Summaries of new PubMed Abstracts delivered to your In-box?

Enter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!