Journal of Intelligent & Fuzzy Systems - Volume 36, issue 1

Authors: Ghareeb, A. | Al-Omeri, Wadei F.

Article Type: Research Article

Abstract: In this paper, we will introduce the notions of semiopenness, semicontinuity, preopenness, precontinuity, irresolutness and preirresolutness degree of functions in (L , M )-fuzzy topological spaces based on the implication operation. Their elementary properties in topology will be extended to the setting of (L , M )-fuzzy topology through graded concepts. Further we characterize and discuss their relationships with the degree of semi(pre)-compactness, semi(pre)-connectedness, Semi - T 1 , Pre - T 1 , Semi - T 2 , and Pre - T 2 .

Keywords: (L, M)-fuzzy topological space, semiopen function, semicontinuous function, irresolute function, semi-homomorphism, preopen function, precontinuous function, preirresolute function, pre-homomorphism

DOI: 10.3233/JIFS-18251

Citation: Journal of Intelligent & Fuzzy Systems, vol. 36, no. 1, pp. 787-803, 2019

Authors: Hamidi, Mohammad | Saeid, Arsham Borumand | Smarandache, Florentin

Article Type: Research Article

Abstract: This paper introduces the concept of single–valued neutrosophic EQ –subalgebras, single–valued neutrosophic EQ –prefilters and single–valued neutrosophic EQ –filters. We study some properties of single–valued neutrosophic EQ –prefilters and show how to construct single–valued neutrosophic EQ –filters. Finally, the relationship between single–valued neutrosophic EQ –filters and EQ –filters are studied.

Keywords: (hyper)single–valued neutrosophic EQ–algebras, single–valued neutrosophic EQ–filters

DOI: 10.3233/JIFS-18424

Citation: Journal of Intelligent & Fuzzy Systems, vol. 36, no. 1, pp. 805-818, 2019

Authors: Guan, Hao | An, Zhiyong

Article Type: Research Article

Abstract: Visual tracking is a very challenging task in computer vision. In this paper, we present a general-purpose framework for robust tracking. We propose to couple one-shot learning and online discriminative learning together to address the fundamental stability-plasticity issue for tracking. A one-shot learner through offline training on large-scale datasets is used as a stable detector which does not suffer model drift while an online discriminative learner is adopted as the tracker which is adaptive to significant appearance changes. Based on the directive framework, we design a baseline tracking model to verify its effectiveness. In practice, a deep Siamese network trained …offline plays as the one-shot learner which can re-detect the target in case of tracking drift and failure. A correlation classifier which incorporates a translation model and a scale model plays as the online learner. Through the coupling of the offline and online learning, the simple baseline tracker achieves a good balance between stability and adaptivity without time-consuming optimization. Experimental results on the large-scale benchmark dataset demonstrate the effectiveness of the proposed framework within which the designed baseline tracker outperforms many state-of-the-art methods both in precision and robustness. Show more

Keywords: Visual tracking, one-shot learning, online learning, deep learning

DOI: 10.3233/JIFS-18577

Citation: Journal of Intelligent & Fuzzy Systems, vol. 36, no. 1, pp. 819-828, 2019

Authors: Wang, Hongzhou

Article Type: Research Article

Abstract: In this paper, we discuss two point boundary value problems of second-order fuzzy boundary value problem. Using monotone iterative method, we investigate the existence of solutions to boundary value problem of fuzzy integro-differential equation firstly, then the results are applied to discuss second-order fuzzy boundary value problem.

Keywords: Second-order fuzzy differential equation, boundary value problem, monotone iterative method

DOI: 10.3233/JIFS-18721

Citation: Journal of Intelligent & Fuzzy Systems, vol. 36, no. 1, pp. 829-838, 2019