Computational Intelligence (CI) is an emerging area of fundamental and applied research in the theory and design of intelligent systems. The particular form of CI research carried out in this laboratory includes Computer vision that includes space-time applications as well as signal value views of optical flow in video frames, video frame foreground moving object tracking, properties and categories (see, e.g., E. Cui, J.F. Peters, Self-similarities in optical flows in CI Lab publications) under publications.

Near sets that includes descriptive proximity spaces and proximal conjugacy as well as a broad range of applications of proximal signals (see, e.g., J.F. Peters, T. Vergili, Fixed point property of amenable planar vortexes. Appl. Gen. Topol. 22 (2021), no. 2, 385-397, under publications, and M. Shangol Haider, Pedestrian Pose Estimation Using Near Set Theory, M.Sc. Thesis, 2021, under dissertations,

Machine learning that includes video frame foreground detection and classification (see, e.g., M.S. Haider, J.F. Peters, Temporal proximiities: self-similar temporally close shapes, Chaos, Solitons and Fractals 151 (2021), 111237, https://doi.org/10.1016/j.chaos.2021.111237 and

Digital image processing that includes voxel lumens flux self-similarities, discrete as well as continuous analysis of image cell complexes (see, e.g., M. Borkowski, Digital image processing in measurement of ice thickness on power lines, M.Sc. thesis, 2002).

Computational topology that includes applications in the graphics derived from transforms of cell complex signals found in the absorption and reflected light from curved surfaces such as river ice, plants, road and building surfaces (see, e.g., under dissertations and Arjuna Philipu Hewa Don, Video Sharpness Barcodes with Bessel Functions and Quaternions, Ph.D. thesis, 2022 and A. Don , J.F. Peters, S. Ramanna, A. Tozzi: Quaternionic views of rs-FMRi hierarchical brain activation regions. Discovery of multilevel brain activation region intensities in rs-FRMI video frames, Chaos, Solitons and Fractals 152 (2021), 111351, Paper.

Image Analysis and Object Detection This is a very active CI Lab research area in image signal tracking and analysis, image classification, and image quality estimation (see list of CI Laboratory Publications).

Machine Learning In recent years, considerable work has been done by this research group on theory and application of adaptive learning. A biproduct of this research has been the design of design of video frame foreground object detection, adaptive telegaming systems and target-tracking systems that learns. Learning is carried out in episodic, ethological, approximation, space-time frameworks. (see list of CI Laboratory Publications).

Near sets are disjoint sets that are resemble each other. One set X is near another set Y to the extent that the description of at least one of the objects in X is similar to the description of at least one of the objects in Y. The hallmark of near set theory is object description and the classification of objects by means of features. Research in near sets includes approach spaces, definable sets, merotopic spaces, metric spaces, nearness spaces, object description, proximity spaces, tolerance spaces, and topology. The near set approach has proven useful in AI applications, digital image (picture) analysis and retrieval, pattern recognition, target tracking (see, e.g., J.F. Peters, T. Vergili, Fixed point property of amenable planar vortexes, Applied General Topology 22 (2021), no. 2, 385-387, under publications.

The CI laboratory engages in fundamental as well as applied research in Computational Intelligence. In parallel to ongoing research projects, the objective of the Laboratory is to provide the community with fully updated information on CI. It is an indispensable source of current information encompassing internal reports, relevant publications and providing with a number of links to selected sites worldwide.