This article introduces fuzzy analogical reasoning by presenting it as an essential component of a global fuzzy reasoning process to be developed. The conceptual framework for urban dialogue systems enables such systems to emulate human analogical reasoning by using cognitive computing, particularly soft computing. This framework is already in the second iteration of its development. Two experiments were conducted to confirm the stability of the theoretical foundation of the framework, and eight experts evaluated it. Based on the experimental findings, the authors have extended the framework with a complementary component focused on knowledge management. Therefore, this article also introduces network-like memory that can be used to retrieve the information needed for the fuzzy analogical reasoning process. The proposed approach for knowledge management is based on the use of fuzzy cognitive maps that can be stored in graph databases.

The exponentially rising amounts of urban data demand new conceptual and technical methods for their management and storage. The era of the Semantic Web requires a convergence toward commonly shared meanings. The combination of fuzzy cognitive maps with graph databases is a first approach to a solution. This article determines the basic requirements for the storing of fuzzy cognitive maps to test current graph databases for their structural suitability. Six out of 47 graph databases fulfill the requirements and are thus recommended for further research purposes. As a proof of concept, OrientDB is used to present how a semantic convergence can be reached through the combination of fuzzy cognitive maps and graph databases in a cognitive city by tackling fuzziness.

This paper presents a software prototype of a personal digital assistant 2.0. Based on soft computing methods and cognitive computing this mobile application prototype improves calendar and mobility management in cognitive cities. Applying fuzzy cognitive maps and temporal algebra, the prototype represents a next step towards the realization of cognitive cities (i.e., smart cities enhanced with cognition). A user scenario and a test version of the prototype are included for didactical reasons.

The Virtual Navigator (VN) technology was used for the fusion of transcranial Ultrasound (US) and brain Magnetic Resonance Images (MRI), with a repeatability error under 0.1 cm. The superimposition of US to the previously acquired MRI volume consisted of external point-based registration, that was subsequently refined with image-based registration of internal brain structures. The common registration procedure with the usage of external fiducial markers acquired with the two modalities was improved using facial anatomical landmarks, with a reduction of the internal targeted structure residual shift (maximum 0.7 cm in the cranio-caudal direction). This allowed the investigation of Deep Cerebral Veins and dural sinuses insonated from the condyloid process of the mandible, a recently introduced US window. The fusion of these vessels to the MRI volume provided their anatomical position and helped excluding false Doppler signal sources.