A new cognitive architecture for artificial vision is proposed. The architecture is aimed for an autonomous intelligent system, as several cognitive hypotheses have been postulated as guidelines for its design. The design is based on a conceptual representation level between the subsymbolic level processing the sensory data, and the linguistic level describing scenes by means of a high-level language. The architecture is also based on the active role of a focus of attention mechanism in the link between the conceptual and the linguistic level. The link between the conceptual level and the linguistic level is modelled as a time-delay attractor neural network.

In most existing SLAM (Simultaneous localization and mapping) methods, it is always assumed that the scene is static. Lots of errors would occur when the camera enters a highly dynamic environment. In this paper, we present an efficient and robust visual SLAM system which associates dynamic feature points detection with semantic segmentation. We obtain the stable feature points by the proposed depth constraint. Combined with the semantic information provided by BlitzNet, every image in the sequence is divided into environment region and potential dynamic region. Then, using the fundamental matrix obtained from the environment region to construct epipolar line constraint, dynamic feature points in the potential dynamic region can be identified effectively. We estimate the motion of the camera using the stable static feature points obtained by the joint constraints. In the process of constructing environment map, moving objects are removed while static objects are retained in the map with their semantic information. The proposed system is evaluated both on TUM RGB-D dataset and in real scenes. The results demonstrate that the proposed system can obtain high-accuracy camera moving trajectory in dynamic environment, and eliminate the smear effects in the constructed semantic point cloud map effectively.

A model for synaptic development in natural perceptive systems based on perturbation theory has been presented during the First Italian Conference on Systemic (; ), and some further refinements and applications have been discussed in Fourth Science European Congress () and in International Conference on Spatial Cognition 2000 (). The underlying idea for the perturbative neural network (PNN) has been suggested by the observation that some synaptic weights of visual system can be interpreted as eigenvectors of a suitable hermitian matrix, which turns out to be the correlation matrix of input vectors.

Recent advances in automatic machine learning (aML) allow solving problems without any human intervention. However, sometimes a human-in-the-loop can be beneficial in solving computationally hard problems. In this paper we provide new experimental insights on how we can improve computational intelligence by complementing it with human intelligence in an interactive machine learning approach (iML). For this purpose, we used the Ant Colony Optimization (ACO) framework, because this fosters multi-agent approaches with human agents in the loop. We propose unification between the human intelligence and interaction skills and the computational power of an artificial system. The ACO framework is used on a case study solving the Traveling Salesman Problem, because of its many practical implications, e.g. in the medical domain. We used ACO due to the fact that it is one of the best algorithms used in many applied intelligence problems. For the evaluation we used gamification, i.e. we implemented a snake-like game called Traveling Snakesman with the MAX–MIN Ant System (MMAS) in the background. We extended the MMAS–Algorithm in a way, that the human can directly interact and influence the ants. This is done by “traveling” with the snake across the graph. Each time the human travels over an ant, the current pheromone value of the edge is multiplied by 5. This manipulation has an impact on the ant’s behavior (the probability that this edge is taken by the ant increases). The results show that the humans performing one tour through the graphs have a significant impact on the shortest path found by the MMAS. Consequently, our experiment demonstrates that in our case human intelligence can positively influence machine intelligence. To the best of our knowledge this is the first study of this kind.

We describe a novel application of deformable templates to automatic shape classification of manufactured (man-made) diamonds. We introduce a new shape parameter, τ, to characterize diamond morphology and describe an approach to compute it from images. Our approach has been implemented in an image analysis system which is currently being used on a regular basis to classify diamonds at a manufacturing facility. An experimental evaluation of the system is given.

To reduce the losses caused by natural disasters such as hurricanes, it is necessary to build effective and efficient emergency management/planning systems for cities. With increases in volume, variety and acquisition rate of urban data, major opportunities exist to implement data-oriented emergency management/planning. New York/New Jersey metropolitan area is selected as the study area. Large datasets related to emergency management/planning including, traffic operations, incidents, geographical and socio-economic characteristics, and evacuee behavior are collected from various sources. Five related case studies conducted using these unique datasets are summarized to present a comprehensive overview on how to use big urban data to obtain innovative solutions for emergency management and planning, in the context of complex urban systems. Useful insights are obtained from data for essential tasks of emergency management and planning such as evacuation demand estimation, determination of evacuation zones, evacuation planning and resilience assessment.

Zusammenfassung

Weltweit arbeitet eine große Zahl von Wissenschaftlern an der Fragestellung: ‘Wie ist es möglich, mit Hilfe der Computertechnik eine Art Künstliche Intelligenz zu schaffen?’ Seit den frühen sechziger Jahren wurde mit sehr viel Euphorie ein Weg eingeschlagen, bei dem versucht wurde, ausgehend von einer diskreten, symbolischen Repräsentation der Welt, der Beschreibung der Zusammenhänge zwischen Einzelinformationen und der Entwicklung geeigneter inferentieller Mechanismen, kognitive Prozesse zu modellieren. Mit dieser Philosophie wurden große Erfolge erzielt, wenn es beispielsweise darum ging, komplexes Expertenwissen maschinell aufzubereiten, auf hohem Niveau Schach zu spielen, einfache mathematische Theoreme zu beweisen oder Intelligenztests zu bearbeiten. Kognitive und sensorische Fähigkeiten, die wir eher als niedrige Intelligenzleistung bewerten würden, wie z.B. schnelle visuelle Analyse einer Szene, Verstehen gesprochener Sprache oder reaktive Bewegungssteuerungen von Manipulatoren konnten mit diesen Methoden aber meist nur unzureichend gelöst werden.

The problem of designing an information system for locating objects in space is discussed. Using the framework of a cognitive collage, as developed by Tversky (1993), it is argued that redundant information from a variety of media is most useful in constructing a spatial information broker. This approach is supported by examining four case studies in detail, you-are-here maps, information kiosks, an information browser, and library locator system. Implications for design of future navigation systems are discussed.

Abstract

This Paper proposes ZigZag, a new clustering algorithm, that works on categorical variable Cross-classification tables. Zigzag creates simultaneously two partitions of row and column categories in accordance with the equivalence relation ”to have the Same conditional mode” . These two partitions are associated one to one and onto, creating by that way row-column clusters. Thus, we have an efficient KDD tool which we tan apply to any database. Moreover, ZigZag visualizes predictive association for nominal data in the sense of Guttman, Goodman and Kruskal. Accordingly, the prediction rule of a nominal variable Y conditionally to an other X consists in choosing the conditionally most probable category of Y when knowing X and the power of this rule is evaluated by the mean proportional reduction in error denoted by λ_Y/X. It would appear then that the mapping furnished by ZigZag plays for nominal data the Same role as the scattered diagram and the curves of conditional means or the straight regression line plays for quantitative data, the first increased with the values of λ_Y/X and λ_X/Y, the second increased with the correlation ratio or the R².

Automobile manufacturers require sense data to analyse and improve the driving experience. Currently, sensors are physically wired to both data collectors and the car battery, thus the number of wires scale linearly with sensors. We design alternative power and communications subsystems to minimise these wires’ impact on the test environment.