Automated quantitative analysis of EEG data is ubiquitous in clinical neurophysiology research. However, these methods have not been fully adopted in medical practice, specifically to inform clinical diagnosis of neurological disorders. In this paper, some of the benefits and challenges of using these techniques as biomarkers for disease indication and progression are discussed. Examples of baseline EEG (resting state) data acquired with the same system and software from patients diagnosed with four types of neurodegenerative diseases are presented and compared with healthy controls. Overall power spectral density analyses showed clear significant differences in EEG for patient sub-types including enhanced theta power in dementia patients (Alzheimer's and Lewy-body dementia), enhanced beta power in Parkinson's patients (with or without dementia) and reduced Alpha power in Alzheimer's dementia. To assess the discriminating power of resting state EEG spectral measures particularly for differential diagnosis at an individual level, a binary classifier was designed to classify EEG data across conditions after feature dimensionality reduction (PCA). The results were evaluated using the area under classifier's ROC curve (AUC). On average, data acquired during eyes-closed resting state resulted in better classification than eyes-open. The highest classification performance (against healthy control) was obtained for Alzheimer's dementia (AD) and Lewy-body dementia (LBD) with AUC =0.80 in both cases. The least accurate classification results were obtained for Mild Cognitive Impairments (MCI) group. The challenges of using resting state EEG for characterization of MCI is discussed and other examples of EEG biomarkers for MCI based on event-related-potentials in a cognitive test of visual memory are presented. An argument is made for adequate sensitivity/specificity of the current state-of-the-art in data-driven EEG analytics as secondary end-points in clinical trials. However, routine clinical diagnostic at an individual level may require a paradigm shift incorporating techniques of precision medicine and big data analytics. Multi-modal public datasets (including EEG and other imaging/clinical data) and adopting standards/protocols for sharing anonymized data between researchers could likely facilitate development of more reliable biomarkers in clinical practice.

We propose a novel video visual analytics system for interactive exploration of surveillance video data. Our approach consists of providing analysts with various views of information related to moving objects in a video. To do this we first extract each object's movement path. We visualize each movement by (a) creating a single action shot image (a still image that coalesces multiple frames), (b) plotting its trajectory in a space-time cube and (c) displaying an overall timeline view of all the movements. The action shots provide a still view of the moving object while the path view presents movement properties such as speed and location. We also provide tools for spatial and temporal filtering based on regions of interest. This allows analysts to filter out large amounts of movement activities while the action shot representation summarizes the content of each movement. We incorporated this multi-part visual representation of moving objects in sViSIT, a tool to facilitate browsing through the video content by interactive querying and retrieval of data. Based on our interaction with security personnel who routinely interact with surveillance video data, we identified some of the most common tasks performed. This resulted in designing a user study to measure time-to-completion of the various tasks. These generally required searching for specific events of interest (targets) in videos. Fourteen different tasks were designed and a total of 120 min of surveillance video were recorded (indoor and outdoor locations recording movements of people and vehicles). The time-to-completion of these tasks were compared against a manual fast forward video browsing guided with movement detection. We demonstrate how our system can facilitate lengthy video exploration and significantly reduce browsing time to find events of interest. Reports from expert users identify positive aspects of our approach which we summarize in our recommendations for future video visual analytics systems.

The problem considered in this article is how to detect and measure resemblances between swarm behaviours. The solution to this problem stems from an extension of recent work on tolerance near sets and image correspondence. Instead of considering feature extraction from subimages in digital images, we compare swarm behaviours by considering feature extraction from subsets of tuples of feature-values representing the behaviour of observed swarms of organisms. Thanks to recent work on the foundations of near sets, it is possible to formulate a rigorous approach to measuring the extent that swarm behaviours resemble each other. Fundamental to this approach is what is known as a recent description-based set intersection, a set containing objects with matching or almost the same descriptions extracted from objects contained in pairs of disjoint sets. Implicit in this work is a new approach to comparing information tables representing N. Tinbergen's ethology (study of animal behaviour) and direct result of recent work on what is known as rough ethology. Included in this article is a comparison of recent nearness measures that includes a new form of F. Hausdorff's distance measure. The contribution of this article is a tolerance near set approach to measuring the degree of resemblance between swarm behaviours.

A modified table look-up scheme for fuzzy systems is applied to learn and imitate human control strategy in tracking control of an overhead crane. Applications of modeling human behavior are not only designing controllers based on human action, but also learning human behavior for studying it and predicting its response. Learning human behavior in itself is not a new research issue; however, when paying particular attention to its random nature, it is still a challenging problem. Consequently, we focus here on fuzzy learning with a consideration for random nature of human behavior. A computer simulator is developed here for manual control of the crane and the simulation results after learning human control strategy confirm that the new modified method performs better than standard learning method.

A concept of probabilistic fuzzy logic is introduced as a way of representing and/or modeling existing randomness in many real world systems and natural language propositions. The approach is based on combining both the concepts of probability of truth and degree of truth in a unique framework. This combination is carried out in both fuzzy sets and fuzzy rules resulting in the concepts of probabilistic fuzzy sets and probabilistic fuzzy rules, respectively. Having one of these probabilistic elements, a probabilistic fuzzy system is then introduced as a fuzzy-probabilistic model of a complex nondeterministic system. In a simple example, human skepticism about the optimal fuzzy rule base is modeled through substituting a probabilistic fuzzy rule base for a conventional one. The closed loop response of the resulting controller for tank level control is shown through simulation and is compared with a conventional fuzzy controller.