The Sigma-max System Induced from Randomness & Fuzziness and its Application in Time Series Prediction
This paper managed to induce probability theory (sigma system) and possibility theory (max system) respectively from the clearly-defined randomness and fuzziness, while focusing the question why the key axiom of "maxitivity" is adopted for possibility measure. Such an objective is achieved by following three steps: a) the establishment of mathematical definitions of randomness and fuzziness; b) the development of intuitive definition of possibility as measure of fuzziness based on compatibility interpretation; c) the abstraction of the axiomatic definitions of probability/ possibility from their intuitive definitions, by taking advantage of properties of the well-defined randomness and fuzziness. We derived the conclusion that "max" is the only but un-strict disjunctive operator that is applicable across the fuzzy event space, and is an exact operator for extracting the value from the fuzzy sample space that leads to the largest possibility of one. Then a demonstration example of stock price prediction is presented, which confirms that max inference indeed exhibits distinctive performance, with an improvement up to 18.99%, over sigma inference for the investigated application. Our work provides a physical foundation for the axiomatic definition of possibility for the measure of fuzziness, which hopefully would facilitate wider adoption of possibility theory in practice.
Code (0)
등록된 구현이 없습니다.
Tasks
Stock Price PredictionTime SeriesTime Series PredictionSimilar Papers 제목 키워드 기반
Estimation & Recognition under Perspective of Random-Fuzzy Dual Interpretation of Unknown Quantity: with Demonstration of IMM Filter
This paper is to consider the problems of estimation and recognition from the perspective of sigma-max inference (probability-possibility inference), with a focus on discovering whether some of the unknown quantities inv…
PhilosophyMultiple model estimation under perspective of random-fuzzy dual interpretation of unknown uncertainty
This study considered the problem of multiple model estimation from the perspective of sigma-max inference (probability - possibility inference), while focusing on discovering whether certain of the unknown quantities in…
Keypoint EstimationPoint TrackingTime Series ForecastingTime Series PredictionModeling dynamic volatility under uncertain environment with fuzziness and randomness
The problem related to predicting dynamic volatility in financial market plays a crucial role in many contexts. We build a new generalized Barndorff-Nielsen and Shephard (BN-S) model suitable for uncertain environment wi…
Time Series AnalysisFuzziness-based Spatial-Spectral Class Discriminant Information Preserving Active Learning for Hyperspectral Image Classification
Traditional Active/Self/Interactive Learning for Hyperspectral Image Classification (HSIC) increases the size of the training set without considering the class scatters and randomness among the existing and new samples. …
Active LearningGeneral ClassificationHyperspectral Image Classificationimage-classification+1PCM and APCM Revisited: An Uncertainty Perspective
In this paper, we take a new look at the possibilistic c-means (PCM) and adaptive PCM (APCM) clustering algorithms from the perspective of uncertainty. This new perspective offers us insights into the clustering process,…
Clustering