Miroslav Uller

Autonomous agents for air-traffic deconfliction

This contribution presents a deployment exercise of multi-agent technology in the domain of deconflicted air-traffic control among several autonomous aerial vehicles (manned as well as unmanned). Negotiation based deconfliction algorithm have been developed and integrated in the agent-based model of the individual flight. Operation of the underlying multi-agent system has been integrated with freely available, geographical and tactical data sources in order to demonstrate openness of the technology. An additional, web client visualization and access component has been developed in order to facilitate a multi-user, platform independent use of the system. The features and application design is illustrated in the demonstration video clip.

Negotiation-Based Approach to Unmanned Aerial Vehicles

We present a framework for agent based aircraft deconfliction mechanism to enable efficient airspace use by various UAVs during coalition operations. In our approach, each vehicle is autonomous, but cooperative: it actively shares its flight plan with near aircrafts so that potential collisions can be detected and resolved using norm-based system. Non-cooperative and utility-based deconfliction approaches are also discussed as they offer a possibility to achieve more efficient and robust mechanism in the future. System is validated on multi-agent simulation that uses the public online-accessible data from various information sources

Optimized Management of BIG Data Produced in Brain Disorder Rehabilitation

Brain disorders resulting from injury, disease, or health conditions can influence function of most parts of human body. Necessary medical care and rehabilitation is often impossible without close cooperation of several diverse medical specialists who must work jointly to choose methods that improve and support healing processes as well as to discover underlying principles. The key to their decisions are data resulting from careful observation or examination of the patient. We introduce the concept of scientific dataspace that involves and stores numerous and often complex types of data, e.g., the primary data captured from the application, data derived by curation and analytic processes, background data including ontology and workflow specifications, semantic relationships between dataspace items based on ontologies, and available published data. Our contribution applies big data and cloud technologies to ensure efficient exploitation of this dataspace, namely, novel software architectures, algorithms and methodology for its optimized management and utilization. We present its service-oriented architecture using a running case study and results of its data processing that involves mining and visualization of selected patterns optimized towards big and complex data we are dealing with.

Student projects in assistive technologies

The paper presents briefly our educational activities in the area of assistive technologies. We have developed a special course on assistive technologies that uses in practical part project-based approach. We have established a specialized facility where the students can work on their projects. The facility simulates real environment of a smart home and a hospital room. The students can select a topic for a project from our proposals or they can come with their own ideas. In the paper we present results of several student projects that can be in the future used as practical applications for people with special needs. Some of them can be additionally used as games both for children and adults.

A Novel Big Data-Enabled Approach, Individualizing and Optimizing Brain Disorder Rehabilitation

Brain disorders occur when our brain is damaged or negatively influenced by injury, surgery, or health conditions. This chapter shows how the combination of novel biofeedback-based treatments producing large data sets with Big Data and Cloud-Dew Computing paradigms can contribute to the greater good of patients in the context of rehabilitation of balance disorders, a significant category of brain damage impairments. The underlying hypothesis of the presented original research approach is that detailed monitoring and continuous analysis of patient´s physiological data integrated with data captured from other sources helps to optimize the therapy w.r.t. the current needs of the patient, improves the efficiency of the therapeutic process, and prevents patient overstressing during the therapy. In the proposed application model, training built upon two systems, Homebalance—a system enabling balance training and Scope—a system collecting physiological data, is provided both in collaborating rehabilitation centers and at patient homes. The preliminary results are documented using a case study confirming that the approach offers a viable way towards the greater good of a patient.

Motion Prediction Influence on the Pedestrian Intention Estimation Near a Zebra Crossing.

The reported work contributes to the self-driving car efforts, more specifically to scenario understanding from the ego-car point of view. We focus on estimating the intentions of pedestrians near a zebra crossing. First, we predict the future motion of detected pedestrians in a three seconds time horizon. Second, we estimate the intention of each pedestrian to cross the street using a Bayesian network. Results indicate, that the dependence between the error rate of motion prediction and the intention estimation is sub-linear. Thus, despite the lower performance of motion prediction for the time scope larger than one second, the intention estimation remains

THE EFFECT OF SPIRITUALITY/RELIGIOSITY ON REGIONAL BRAIN ATROPHY IN SUBJECTS AT RISK OF ALZHEIMER DISEASE: THREE-YEAR FOLLOW-UP DATA FROM CZECH BRAIN AGING STUDY

P3-564 THE EFFECT OF SPIRITUALITY/ RELIGIOSITY ON REGIONAL BRAIN ATROPHY IN SUBJECTS AT RISK OF ALZHEIMER DISEASE: THREE-YEAR FOLLOW-UP DATA FROM CZECH BRAIN AGING STUDY Katerina Sheardova, Zuzana Nedelska, Rastislav Sumec, Rafal Marciniak, Miroslav Uller, Jakub Hort, Department of Neurology, St. Anne’s University Hospital Brno, Brno, Czech Republic; International Clinical Research Center, St. Anne’s University Hospital Brno, Brno, Czech Republic; Memory Clinic, Department of Neurology, 2nd Faculty of Medicine, Charles University andMotol University Hospital, Prague, Czech Republic; Masaryk University, Brno, Czech Republic. Contact e-mail: ksheardova@gmail.com

DISTINCT SPATIAL NAVIGATION IMPAIRMENT ACROSS NEURODEGENERATIVE DEMENTIAS AND ITS NEUROANATOMICAL UNDERPINNINGS

decline is increased substantially by the presence of at least one copy of the APOE ε4 allele. Despite advances in Ab biomarkers, age remains the greatest risk factor for dementia, particularly Alzheimer’s disease (AD). As APOE ε4 increases risk for Ab+ and older adults are also more likely to be Ab+, it is important to understand the extent to which age influences the effects of ε4 on Ab+ related memory decline. This study aimed to determine the extent towhich theAPOE ε4 allele influenced Ab related cognitive change in adults aged between 60-74 and 75-90 years old. Methods:Nondemented adults (n1⁄4485) enrolled in the AIBL study underwent Ab neuroimaging and ε4 genotyping. Episodic Memory was assessed at baseline, 18-, 36-, 54and 72-month follow-ups. Participants were classified as Abor Ab+ using PET neuroimaging and into two age groups (<75 and 75) according to their age at baseline. Data were analysed using linear mixed model analyses. Results:In adults aged<75, when compared to the Abgroup, there was a significant rate of memory decline only in Ab+ ε4 carriers (d1⁄41.25). In adults aged 75, when compared to the Abgroup, both Ab+ ε4 carriers (d1⁄41.23) and non-carriers (d1⁄40.35) showed significant rates of memory; however, the memory decline in Ab+ ε4 carriers was substantially greater when compared to noncarriers (d1⁄40.82). This faster rate of memory decline in adults aged 75 was reflected in a 43% of Ab+ ε4 carriers meeting clinical criteria for dementia at the 72-month assessment, in contrast to just 24% of Ab+ ε4 non-carriers and 10% of Abparticipants. Conclusions:Previous studies investigating the relationship between ε4 andAb+have not accounted for potential non-linear effects of age on memory decline. The rate of Ab+ related memory decline was greatest in adults aged 75, particularly in those who were also APOE ε4 carriers. This suggests that the combined effects of Ab+ and ε4 on risk for dementia increases substantially in older adults.

SUBJECTIVE COGNITIVE COMPLAINTS REFLECT HIPPOCAMPAL ATROPHY IN NONDEMENTED OLDER ADULTS AS WELL AS OBJECTIVE MEMORY TESTING

Background: Self-reported subjective cognitive decline (SCD) could represent an early sign of Alzheimer’s disease (AD). Yet, the type of cognitive complaint associated with preclinical AD needs to be refined. We aimed at identifying specific types of complaint associated with i) medical help seeking, ii) the presence of actual memory impairment among patients referring to a memory clinic. We also assessed whether specific patterns of complaints were associated with neuroimaging biomarkers. Methods: We included three groups of nondemented elder individuals (Fig1): i) Healthy Aged Subjects (HAS, n1⁄461), ii) patients from a memory clinic with SCD but normal neuropsychological assessment (SCD, n1⁄429), iii) patients with amnestic Mild Cognitive Impairment (aMCI, n1⁄473). Participants filled the Cognitive Difficulty Scale questionnaire (CDS), consisting of 39 items on a 5-point scale. They underwent cognitive assessment, structural MRI and a subgroup had Florbetapir-PET to assess Ab burden. The questionnaire was analyzed in two complementary ways. First, between-group comparisons were conducted item-by-item using non-parametric tests to identify items related to medical help seeking (HAS<SCD) or cognitive impairment (SCD<MCI). Second, exploratory factor analysis was conducted on the full group, using a method adapted to ordinal data. Results: Compared to HAS, both SCD and MCI patient groups reported comparable complaint, mainly on attentional and memory items (Fig2, top). Only one item, assessing temporal orientation, discriminated between SCD and MCI patients; in the latter group, self-reported temporal disorientation was associated with worse memory and higher Ab burden (Fig2, bottom). The factor analysis identified 3 factors accounting for 54% of total variance. Factors 1 (general cognition/attention) and 2 (temporal orientation/memory) differed between groups (Fig 3, top) and were associated with anxiety but neither memory performances nor age. In MCI, the pattern of complaint depended on Ab status (fig 3, bottom): Ab+ patients reported strong orientation/memory difficulties and little attentional troubles while Abpatients had mixed complaints with a strong attentional component. Conclusions:Detailed assessment of patients’ self-reported difficulties is associated with clinical and cognitive features, as well as the presence of Ab in patients with MCI. Probing self-reported disorientation in addition to memory could have strong implications for early AD detection.