The International Journal of Fuzzy Logic and Intelligent Systems (pISSN 1598-2645, eISSN 2093-744X) is published quarterly by the Korean Institute of Intelligent Systems. The official title of the journal is International Journal of Fuzzy Logic and Intelligent Systems and the abbreviated title is Int. J. Fuzzy Log. Intell. Syst. Some, or all, of the articles in the journal are indexed in SCOPUS, Korea Citation Index (KCI), DOI/CrossrRef, DBLP, and Google Scholar, and Emerging Sources Citation Index (ESCI).
The journal was launched in 2001 and dedicated to the dissemination of well-defined theoretical and empirical studies results that have a potential impact on the realization of intelligent systems based on fuzzy logic and intelligent systems theory. Specific topics include, but are not limited to: a) computational intelligence techniques including fuzzy logic systems, neural networks and evolutionary computation; b) intelligent control, instrumentation and robotics; c) adaptive signal and multimedia processing; d) intelligent information processing including pattern recognition and information processing; e) machine learning and smart systems including data mining and intelligent service practices; f) fuzzy theory and its applications.
Sangyun Lee and Sungjun Hong
International Journal of Fuzzy Logic and Intelligent Systems 2022;22: 339-349 https://doi.org/10.5391/IJFIS.2022.22.4.339Hamzeh Zureigat, Abd Ulazeez Alkouri, Areen Al-khateeb, Eman Abuteen, and Sana Abu-Ghurra
International Journal of Fuzzy Logic and Intelligent Systems 2023;23: 11-19 https://doi.org/10.5391/IJFIS.2023.23.1.11Hamzeh Zureigat, Abd Ulazeez Alkouri, Areen Al-khateeb, Eman Abuteen, and Sana Abu-Ghurra
International Journal of Fuzzy Logic and Intelligent Systems 2023;23: 11-19Sangyun Lee and Sungjun Hong
International Journal of Fuzzy Logic and Intelligent Systems 2022;22: 339-349Architecture of a conventional SCNN. The network is trained by contrastive loss in the training stage, whereas a distance function is used to compute the similarity metric in the testing stage.
|@|~(^,^)~|@|The proposed ESCNN architecture, which consists of three parts: (a) Siamese, (b) extension, and (c) decision parts. The feature dimensions are denoted as
Visualization of the features learned by the ESCNN: (a) positive and (b) negative samples.
|@|~(^,^)~|@|Training strategy of the proposed network. The network is optimized by a combination of two loss functions: 1) contrastive loss for the Siamese part and 2) cross-entropy loss for all parts, including the extension and decision parts.
|@|~(^,^)~|@|Examples from the iLIDS–VID dataset.
|@|~(^,^)~|@|Some example results: (a) positive and (b) negative samples.
|@|~(^,^)~|@|ROC curves for the methods under consideration.