Search

During any crisis, part of the perception of risk is subjective and evolves as new insights become available. Risk awareness and even the reaction to occurrences of risk—and so the adopted attitude towards risk mitigation—differ depending on the predominant personality dynamics of the decision maker. This is a dimension that should be considered in risk management, and in particular for those risk classes that represent safety, security, and business continuity related risks. This subjectivity in risk management represents a certain concern that should be addressed.

Human interaction is to a large extent based on implicit, unconscious behavior and the related body language. In this article, we propose ‘Directed Effort’ a generic description of human behavior suitable as user engagement and interest input for higher level human-computer interaction applications. Research from behavioral and psychological sciences is consulted for the creation of an attention model which is designed to represent the engagement of people towards generic objects in public spaces. The functionality of this behavior analysis approach is demonstrated in a prototypical implementation to present the potential of the presented meta-level description of behavior.

In this study, we proposed an emotion generation model for robots that considers mutual effects of desires and emotions. Many researchers are developing partner robots for communicating with people and entertaining them, rather than for performing practical functions. However, people quickly grow tired of these robots owing to their simplistic emotional responses. To solve this issue, we attempted to implement the mutual effects of desires and emotions using internal-states, such as physiological factors. Herein, the simulation results verified that the proposed model expresses complex emotions similar to humans. The results confirmed that the emotions expressed by the proposed model are more complex and realistic than those expressed by a reference model.

This work proposes a computational approach supporting the simulation of human automation interaction in aviation. The development of an advanced human agent model that accounts for workload limitations, imperfect mental models and consequences on the operator's situation awareness provides new insight for future certification procedures regarding human interaction with complex automated systems.

Automatic, fast and accurate extraction of the blood vessel is an important task in the image-aided diagnosis of disease. In this paper, we describe a novel superficial vessel imaging and projecting system. First, the superficial vessel of human arm is captured by NIR imaging technique, and then three pre-processing algorithms, including hair removal, non-uniform illumination correction and vessel enhancement, are developed to strengthen the vessel image. Second, a model-based binarization method is proposed to detect vessel-like structures. And then the mathematic morphological and connected component refinement methods are integrated to remove small vessel noises. Experimental results demonstrate that our system can imaging superficial vessels on real-time. The proposed system does not need any human interaction, which hence can be used in clinical venipuncture practices.

Human Action Recognition (HAR) has centered the interest of much research in the last years. Most of this interest has been focused on recognizing motion behavior from a single person (run, jump, walk, hand-wave, etc). However, Human Interaction Recognition (HIR) focus on those cases where several people participate in the scene but the action is carried out only by some of them. The HIR-task is a harder problem than the HAR-task and heretofore very modest scores have been achieved on realistic scenarios. In this paper, we present a new approach to the HIR-task from decoupling the camera and subject motion and using SVM multiple instance learning classifiers. In addition, the pyramidal PaHOF descriptor proposed in the HAR-task context has been adapted. Experimental results on the very challenging TV Human Interactions Dataset [12] are shown, supporting the validity of the proposed approach.

The spatial-orientational organization of face-to-face conversational encounters can be described in terms of the sociological notion of F-formations. Ethnomethodological studies of human interaction indicate several geometrical constraints that influence the positional orientations assumed by participants of F-formations. By incorporating some of these constraints, a computational system has been developed that enables agents to dynamically plan their spatial whereabouts in a virtual environment. This paper presents the system and analyses its impact in leading to the emergence of F-formation like spatial configurations in a two-dimensional multi-agent environment. Analyses are based on how experimental subjects perceived the groupings of agents in the virtual environment.

This poster describes a transdisciplinary practical-theoretical on-going research, which address on the discussion about the possible applications of Artificial Intelligence (AI) techniques, such as genetic algorithms, which underlie the Maturana and Varela’s autopoietic concept considering the achievement of emergent results as heuristic to creativity. Through human interaction using neuronal bio-feedback it is possible to provide more natural fitness function to such algorithms.

In this paper, we focus on the recognition and localization of human interactions in real-world videos. It is a difficult challenge because of large variations in person appearance, camera viewpoint, length of video, intra-class variability, and etc. To address these challenges, we present a spatial structure model in this paper. In our model, the crucial movement of each category is represented using a segment of the entire video. To capture the spatial configuration of the human interactions within the video segment, a spatial structure model is built over the segment, and trajectory features are extracted within each cell. The proposed model is trained automatically from real-world videos that are annotated only with the classification label. We examine our approach on the TVHI dataset, which contain 4 complex human interaction action classes. The experimental results demonstrate the effectiveness of our model.

In modern life, interactions between human beings frequently occur in meetings, where topics are discussed. Semantic knowledge of meetings can be revealed by discovering interaction patterns from these meetings. An existing method mines interaction patterns from meetings using tree structures. However, such a tree-based method may not capture all kinds of triggering relations between interactions, and it may not distinguish a participant of a certain rank from another participant of a different rank in a meeting. Hence, the tree-based method may not be able to find all interaction patterns such as those about correlated interaction. In this paper, we propose to mine interaction patterns from meetings using an alternative data structure - namely, a directed acyclic graph (DAG). Specifically, a DAG captures both temporal and triggering relations between interactions in meetings. Moreover, to distinguish one participant of a certain rank from another, we assign weights to nodes in the DAG. As such, a meeting can be modeled as a weighted DAG, from which weighted frequent interaction patterns can be discovered. Experimental results showed the effectiveness of our proposed DAG-based method for mining interaction patterns from meetings. © Springer-Verlag 2013.

This article describes a new collection of still image dataset which are dedicated to interactions between people. Human action recognition from still images have been a hot topic recently, but most of them are actions performed by a single person, like running, walking, riding bikes, phoning and so on and there is no interactions between people in one image. The dataset collected in this paper are concentrating on human interaction between two people aiming to explore this new topic in the research area of action recognition from still images.

This paper examines how Spohn's Ordinal Conditional Functions, which are used to model belief dynamics, when appropriately adapted and interpreted, can fruitfully model the dynamics of trust. In this framework, trust is defined in terms of lack of trust (trust deficit) which is taken to be a primitive notion. It explores the notion of context sensitive trust, i.e., how in different domains of human interaction, one agent might trust another agent in varying degrees, and suggests the dynamics of such trust.

The reduction in human interaction costs enabled by social computing technologies has created opportunities for companies to reduce the cost of growth and of innovation both by getting much more value out of their own personnel and by using people they do not employ to create value for them, either gratis, or for a fee to be paid only after the value is created. Recognition of these opportunities is driving business reorganization by “early adopter” companies pursuing the benefits to be derived from business applications of social computing. These benefits are anchored in the growing centrality to wealth creation of continuous innovation. Continuous innovation, in turn, is critically dependent on tacit interactions among people, that is, on interactions that provide access to implicit, as well as explicit, knowledge, information, experience and expertise possessed by possibly very large numbers of people, who may be widely distributed, organizationally, and even globally.

The first step for building reliable humanoid systems is to provide them with perceptual mechanisms that have human attributes, such as the skill development, social interaction, environmental embodiment and sensorial integration. Despite tactile perception being one of the most important elements for human interaction with the world, its implementation within artificial systems has been tardy, principally because it requires a complete integration with the motor systems and an environmental coupling to extract comprehensible information [1]. Thus, this work aims to generate a platform based on haptic information, allowing humanoids to perceive and represent surrounding objects using concepts fully grounded in the sensorial data.

A significant number of attacks on systems are against the non-cryptographic components such as the human interaction with the system. In this paper, we propose a taxonomy of human-protocol interaction weaknesses. This set of weaknesses presents a harmonization of many findings from different research areas. In doing so we collate the most common human-interaction problems that can potentially result in successful attacks against protocol implementations. We then map these weaknesses onto a set of design recommendations aimed to minimize those weaknesses.

To enhance human interaction with machines, research interest is growing to develop a ’Brain-Computer Interface’ (BCI), which allows communication of a human with a machine only by use of brain signals. In this paper, one type of pocket PC game was designed for application of brain computer interfaces. In this system, The cerebral cortex EEG based on motor imagery were fed into the input of signal processing module, and then classification algorithm module of motor imagery deal with this signal. Output results for classification of motor imagery were converted to control the role in the games. The result of experiment shows that BCI technology not only can be used for rehabilitation, but also can be used for general public entertainment.

Communication is an essential element of human interaction with a community. People with communication disorders that would otherwise impede this interaction can interface with their communities via augmentative and alternative communication. The Korean government supports these disabled people with augmentative and alternative communication devices. However, most devices require high cost and have only simple functions. Furthermore, they require space for storage. As an effort to relieve the difficulties of using such devices, this study develops an augmentative and alternative communication application that can be mounted on widely spreading smart-phones and tablet PCs.

As the basis of generating nonverbal expressions in animated agents, this paper proposes factors that account for cultural difference in nonverbal behaviors in negotiation interaction. First, we introduce theories of negotiation and cultural characteristics. Then, our analysis of human interaction in negotiation conversations in CUBE-G corpus is described. Finally, by integrating cultural and negotiation parameters with empirical data obtained in the corpus analysis, we design a parameterized network model that generates culture specific nonverbal expressions in negotiation conversations.

In recent years, the use of presentations as an efficient method for communication has been proven to play a significant role in professional research activities, especially from the standpoint of education and business in enterprises. In these scenarios, this method is intended to clearly convey information from the presenter to the audience in a limited time, and to garner active feedback from the audience by means of human interaction. However, for the majority of presentations, it is difficult to stimulate the audiences to comment and discuss the topic, as well as to receive sufficient comments in a limited time. For these reasons, we have attempted to devise a system that provides a function for collecting the maximum possible comments in a time-limited presentation. By increasing the possibilities offered to presenters for handling such situations, and to remind both the presenters and audiences of the pace of the presentation, we conducted an experiment to prove that the approach used in our system is effective.