Adam Csapo

Object Categorization Using VFA-generated Nodemaps and Hierarchical Temporal Memories

Object categorization and recognition have proved to be difficult tasks in artificial intelligence for several decades. With the recent emergence of biologically inspired soft-computing methods, promising results in specialized application domains are more and more common. In this paper, we propose a novel object categorization method based on statistical properties of nodes -derived from the VFA model -and hierarchical temporal memories. A referential categorization method, obtained by feeding grayscale pixel levels to hierarchical temporal memories, is used to evaluate the models performance. Results show that categorization based on the statistics of nodes seems to yield higher success rates. This is in correspondence with Biedermans conjecture in his theory of recognition by components (RBC), according to which the statistics of nodes, end points and corners carry essential and sufficient information for object recognition [1]. The first section of this paper consists of a brief introduction, in which we restate the formal definition of the VFA model, as well as present its node-filtering applications. This will be followed by a presentation of the HTM theory for size-and orientation-invariant object representation. Finally, we give a detailed case study in which a hierarchical temporal memory is used to distinguish between two, as well as several object categories.

An overview of research trends in CogInfoCom

Cognitive infocommunications (CogInfoCom) is an interdisciplinary field that targets engineering applications based on emergent synergies between ICT and the cognitive sciences. The unique perspective of CogInfoCom enables researchers to focus on both the qualitative and quantitative analysis of cognitive capabilities in application areas where humans are becoming increasingly entangled with and dependent on intelligent networked services. An international conference on the field has been held every year since 2010, and the two most recent events have been supported by the IEEE. In this paper, we provide an overview of the various research directions which have been represented at the conference series, and which have as a result gained strong relevance to CogInfoCom during the past few years.

A survey of assistive technologies and applications for blind users on mobile platforms: a review and foundation for research

This paper summarizes recent developments in audio and tactile feedback based assistive technologies targeting the blind community. Current technology allows applications to be efficiently distributed and run on mobile and handheld devices, even in cases where computational requirements are significant. As a result, electronic travel aids, navigational assistance modules, text-to-speech applications, as well as virtual audio displays which combine audio with haptic channels are becoming integrated into standard mobile devices. This trend, combined with the appearance of increasingly user-friendly interfaces and modes of interaction has opened a variety of new perspectives for the rehabilitation and training of users with visual impairments. The goal of this paper is to provide an overview of these developments based on recent advances in basic research and application development. Using this overview as a foundation, an agenda is outlined for future research in mobile interaction design with respect to users with special needs, as well as ultimately in relation to sensor-bridging applications in general.

Overview of auditory representations in human-machine interfaces

In recent years, a large number of research projects have focused on the use of auditory representations in a broadened scope of application scenarios. Results in such projects have shown that auditory elements can effectively complement other modalities not only in the traditional desktop computer environment but also in virtual and augmented reality, mobile platforms, and other kinds of novel computing environments. The successful use of auditory representations in this growing number of application scenarios has in turn prompted researchers to rediscover the more basic auditory representations and extend them in various directions. The goal of this article is to survey both classical auditory representations (e.g., auditory icons and earcons) and those auditory representations that have been created as extensions to earlier approaches, including speech-based sounds (e.g., spearcons and spindex representations), emotionally grounded sounds (e.g., auditory emoticons and spemoticons), and various other sound types used to provide sonifications in practical scenarios. The article concludes by outlining the latest trends in auditory interface design and providing examples of these trends.

Coginfocom systems from an interaction perspective - A pilot application for EtoCom

Cognitive Infocommunications (CogInfoCom) is a newly emerging research field that investigates the link between infocommunications and the cognitive sciences, with the goal of creating engineering systems in which artificial and natural cognitive systems can work together more effectively. In this paper, we describe the structure of CogInfoCom systems from an interaction perspective. Through the discussions in this paper, our goal is to further clarify the relationship between CogInfoCom and the various research areas that deal with behavioral and structural systems modeling. In order to demonstrate the theoretical aspects of the subject, we describe a pilot application which was developed during the EtoCom project.

CogInfoCom channels and related definitions revisited

An important challenge in CogInfoCom is to design multi-sensory signals which are capable of communicating high-level information to users. The concept of CogInfoCom channels was proposed in order to facilitate both theoretical and practical investigations in this direction. A number of aspects of CogInfoCom channels have been treated in earlier papers, however, some of the related definitions have recently undergone changes. The goal of this paper is to concisely summarize the current state of research on CogInfoCom channels.

The Spiral Discovery Method: An Interpretable Tuning Model for CogInfoCom Channels

Cognitive Infocommunications (CogInfoCom) messages that are used to carry information on the state of the same high-level concept can be regarded as belonging to a CogInfoCom channel. Such channels can be generated using any kind of parametric model. By changing the values of the parameters, it is possible to arrive at a large variety of CogInfoCom messages, a subset of which can belong to a CogInfoCom channel -provided they are perceptually well-suited to the purpose of conveying information on the same highlevel concept. Thus, for any CogInfoCom channel, we may speak of a parameter space and a perceptual space that is created by the totality of messages in the CogInfoCom channel. In this paper, we argue that in general, the relationship between the parameter space and the perceptual space is highly non-linear. For this reason, it is extremely difficult for the designer of a CogInfoCom channel to tune the parameters in such a way that the resulting CogInfoCom messages are perceptually continuous, and suitable to carry information on a single high-level concept. To address this problem, we propose a cognitive artifact that uses a rank concept available in tensor algebra to provide the designer of CogInfoCom channels with practical tradeoffs between complexity and interpretability. We refer to the artifact as the Spiral Discovery Method (SDM).

An interaction-based model for auditory substitution of tactile percepts

We refer to channels of communication that link the user to information systems as cognitive communication channels. One especially interesting research topic related to cognitive communication channels deals with a special application called sensory substitution, when information is conveyed through a channel other than the one that is normally used for the given application. Our goal is to develop engineering systems for the remote teleoperation of robots using sensory substitution to convey feedback information in meaningful ways. Such applications could help reduce the cognitive load for the user on the one hand, and help alleviate the effect of control instabilities and network delays on the other. A large part of our research deals with how to provide information on physical parameters - otherwise inaccessible to the remote user - through sound. In this paper, we first propose a model that describes the kinds of pairings between physical and auditory parameters we find meaningful. This is followed by a description of an example application in which auditory signals are used to convey information on tactile perception.

An application-oriented review of CogInfoCom: The state-of-the-art and future perspectives

Cognitive Infocommunications (CogInfoCom) is an emerging discipline that investigates synergies between infocommunications and the cognitive sciences, with the goal of creating engineering applications in which systems with various levels of cognitive capability are enabled to work together more effectively. While infocommunications deals with the error-free encoding, transmission and decoding of raw data, CogInfoCom aims to transmit information at a higher, conceptual level in a way that appeals to the receivers cognitive capabilities. Thus, CogInfoCom may have implications for a wide variety of fields in the future, including virtual reality, 3D Internet and Internet of Things. In this paper, we provide a brief, application-oriented overview of the existing background of CogInfoCom, and outline future perspectives for the field.

Special issue on multimodal interfaces in cognitive infocommunication systems

Humans and the infocommunications network surrounding them are merging together at various levels, ranging from the level of interactions with personal devices to the highest level of sensing collective behaviors such as mass movements, mass habits etc. Consequently, humans and infocommunications will soon coexist as an entangled web, resulting in an augmentation and merging of both natural and artificial cognitive capabilities. This process of merging is occurring today, and is expected to gain further impact in the near future. Cognitive infocommunications (CogInfoCom) is an interdisciplinary field that aims to reflect on this process of merging by investigating links between the research areas of infocommunications and the cognitive sciences, as well as the various engineering applications that have emerged as the synergic combination of these sciences. Given the interdisciplinary background of CogInfoCom, many aspects of the synergies behind it can be considered. The papers in this special issue all focus on some aspect of multimodal interfaces in the context of infocommunication systems that enable enhanced cognitive capabilities through the merging of the natural and artificial. Papers range from the more theoretical to those which introduce practical applications. Several papers address multi-modal aspects of human speech. The paper by A. Abuczki focuses on a multi-modal corpus based approach to modeling cognitive, information and interactional states behind speech interactions, basedon a set of discoursemarkers and hand-based gestures. The papers