In the field of driver assistance systems, many methods have been proposed to estimate the alertness of a driver and detect dangerous driver states. This article addresses a complementary problem – given that there is a method for detecting the alertness of a vehicle’s driver, how do we find an effective countermeasure policy to make sure that the driver stays in the alert state, therefore, minimizing safety risks? The article formulates the problem of maintaining driver’s state with a help of active countermeasures as a contextual bandit problem. In particular, it proposes a conceptual schema of the approach, defines problem-specific action loss function, context representation, and implements several contextual bandit algorithms. To evaluate the approach the paper introduces a computational model of a driver’s alertness, based on fatigue research. The performed evaluation with the computational model has shown that all implemented algorithms just after few simulated trips were able to obtain intervention policies significantly surpassing non-personalized baseline.

Ontology-based explanation techniques allow one to get explanation why a neural network arrived to some conclusion using human-understandable terms and their formal definitions. The paper proposes a method to build post-hoc ontology-based explanations by training a multi-label neural network mapping the activations of the specified "black box" network to ontology concepts. In order to simplify training of such network we employ semantic loss, taking into account relationships between concepts. The experiment with a synthetic dataset shows that the proposed method can generate accurate ontology-based explanations of a given network.

Collective intelligence helps to address many problems that are intractable by efforts of a single person. One of the current challenges in building collective intelligence systems is to seamlessly integrate AI agents in them, transforming traditional collective intelligence to human-machine collective intelligence. The paper describes an approach to address two cornerstone problems of human-machine collective intelligence – interoperability in hybrid teams and sustaining the degree of self-organization required to address complex problems. To solve the first problem, it is proposed to leverage the expressiveness of ontologies and the technology of ontology-based smart spaces. To address the second one, a concept of assisted self-organization is proposed, including a method to assist in team-formation and a method to detect and resolve non-productive situations in the collective work.

The paper describes a human-computer cloud environment supporting the deployment and functioning of human-based applications and allowing to decouple computing resource management issues (for this kind of applications) from application software. The paper focuses on two specific contributions lying in the heart of the proposed human-computer cloud environment: a) application platform, allowing to deploy human-based applications and using digital contracts to regulate the interactions between an application and its contributors, and b) the principles of ontology-based decision support service that is implemented on top of the human-computer cloud and uses task decomposition in order to deal with ad hoc tasks, algorithms for which are not described in advance.

A collective intelligence system could significantly help to improve decision making. Its advantage is that often collective decisions can be more efficient than individual ones. The paper considers the human-machine collective intelligence as shared intelligence, which is a product of the collaboration between humans and software services, their joint efforts and conformed decisions. Usually, multiple collaborators do not share a common view on the domain or problem they are working on. The paper assumes usage of multi-aspect ontologies to overcome the problem of different views thus enabling humans and intelligent software services to self-organize into a collaborative community for decision support. A methodology for development of the above multi-aspect ontologies is proposed. The major ideas behind the approach are demonstrated by an example from the smart city domain.

The concept of human-computer cloud is an adaptation of a traditional cloud computing paradigm to applications that require human expertise for performing some of the information processing operations. In these environments, it is important to maintain rich contributor profile that would allow to automatically route task requests to the contributors who will most likely complete them with high quality. On the other hand, the burden of filling and updating the profile shouldn't be entirely on the shoulders of contributors. This paper describes the profile structure of human-computer cloud environment and several mechanisms for automatically filling it and keeping up-to-date.

Tourist mobility, high risk and uncertainty in unfamiliar environments cause the importance of information and decision support for tourists. On the other side, complex nature of tourism economic sector, intertwined with other sectors, demand for decision support methodologies and tools helping destination management organizations to plan the activities for promoting and rational development of tourist destinations. Decision support systems in tourism today leverage a variety of technologies both machine-driven and human-driven. This paper applies a novel concept of human-computer cloud as a conceptual and architectural approach to building decision support systems in tourism (both from the tourist's perspective, and from destination management organization's perspective). The main role of human-computer cloud here is to provide a convenient abstraction for computational resources, not only "ordinary" (electronic/software) ones but also human-based. In the paper, we identify the list of typical decision support tasks in tourism domain, outline possible human-based extensions of traditional kinds of decision support systems, and finally discuss how some popular decision support functions in this domain can be mapped to a multi-tiered conceptual architecture of human-computer cloud services. The proposed approach is illustrated by two usage scenarios - itinerary planning and destination visitors' survey.