Abstract: The paper advocates a new concept for risk control that makes up one organic closed loop feedback system, with the following stages: 1) the evaluation of the positive and negative features of situation under investigation through strengths, weaknesses, opportunities, and threats (SWOT) analysis, 2) the determination of the level of fuzzy risk concealed in this situation (using RISK evaluation), and 3) the proposal of leverage, recommendations, or actions (through LEVERAGE aggregation) enabling the improvement of target performance. Useful fundamental approaches, definitions, and particularities of this concept concerning SWOT, RISK and LEVERAGES are examined, and for the first time the network type called here the fuzzy SWOT map (FSM) is introduced. This newly proposed instrument appeared as a result of a natural extension of fuzzy cognitive maps paradigm enhanced by dynamic computing with words (CWW) elements and possibilities to use the explainable artificial intelligence (XAI) in the form of fuzzy inference rules. The concept serves for development of functional organization of control systems of complex and dynamically interacting projects or situations and for implementation of adequate set of tools satisfying the concrete system’s requirements. The results of conceptual modeling and the confirmation of the vitality of the approach are presented based on the simplified example of a risk-control system case covering three interacting projects in a complex environment of city development.Abstract: The paper advocates a new concept for risk control that makes up one organic closed loop feedback system, with the following stages: 1) the evaluation of the positive and negative features of situation under investigation through strengths, weaknesses, opportunities, and threats (SWOT) analysis, 2) the determination of the level of fuzzy risk conce...Show More
Abstract: Deep learning has attracted a lot of attention lately, thanks. Thanks to its high modeling performance, technological advancement, and big data for training, deep learning has achieved a remarkable improvement in both high and low-level vision tasks. One crucial aspect of the success of a deep learning-based model is an adequate large data set for fueling the training stage. But in many cases, well-labeled large data is hard to acquire. Recent works have shown that it is possible to optimize denoising models by minimizing the difference between different noise instances of the same image. Yet, it is not a common practice to collect data with different noise instances of the same sample. Addressing this issue, we propose a training method that enables training deep convolutional neural network models for Gaussian denoising to be trained in cases of no ground truth data. More specifically, we propose to train a deep learning-based denoising model using only a single noise instance. With that in mind we develop a non-local self-similarity noise training method that uses only one noise instance.Abstract: Deep learning has attracted a lot of attention lately, thanks. Thanks to its high modeling performance, technological advancement, and big data for training, deep learning has achieved a remarkable improvement in both high and low-level vision tasks. One crucial aspect of the success of a deep learning-based model is an adequate large data set for ...Show More
