Body posture and finger pointing are a natural modality for human-machine interaction, but first the system must know what it's seeing.

Vision-based hand-gesture applications

This paper systematically develops a set of general and supporting design principles and specifications for a "Dynamic Emergency Response Management Information System" (DERMIS) by identifying design premises resulting from the use of the "Emergency Management Information System and Reference Index" (EMISARI) and design concepts resulting from a comprehensive literature review. Implicit in crises of varying scopes and proportions are communication and information needs that can be addressed by today's information and communication technologies. However, what is required is organizing the premises and concepts that can be mapped into a set of generic design principles in turn providing a framework for the sensible development of flexible and dynamic Emergency Response Information Systems. A framework is presented for the system design and development that addresses the communication and information needs of first responders as well as the decision making needs of command and control personnel. The framework also incorporates thinking about the value of insights and information from communities of geographically dispersed experts and suggests how that expertise can be brought to bear on crisis decision making. Historic experience is used to suggest nine design premises. These premises are complemented by a series of five design concepts based upon the review of pertinent and applicable research. The result is a set of eight general design principles and three supporting design considerations that are recommended to be woven into the detailed specifications of a DERMIS. The resulting DERMIS design model graphically indicates the heuristic taken by this paper and suggests that the result will be an emergency response system flexible, robust, and dynamic enough to support the communication and information needs of emergency and crisis personnel on all levels. In addition it permits the development of dynamic emergency response information systems with tailored flexibility to support and be integrated across different sizes and types of organizations. This paper provides guidelines for system analysts and designers, system engineers, first responders, communities of experts, emergency command and control personnel, and MIS/IT researchers. SECTIONS 1. Introduction 2. Historical Insights about EMISARI 3. The emergency Response Atmosphere of OEP 4. Resulting Requirements for Emergency Response and Conceptual Design Specifics 4.1 Metaphors 4.2 Roles 4.3 Notifications 4.4 Context Visibility 4.5 Hypertext 5. Generalized Design Principles 6. Supporting Design Considerations 6.1 Resource Databases and Community Collaboration 6.2 Collective Memory 6.3 Online Communities of Experts 7. Conclusions and Final Observations 8. References 1. INTRODUCTION There have been, since 9/11, considerable efforts to propose improvements in the ability to respond to emergencies. However, the vast majority of these efforts have concentrated on infrastructure improvements to aid in mitigation of the impacts of either a man-made or natural disaster. In the area of communication and information systems to support the actual ongoing reaction to a disaster situation, the vast majority of the efforts have focused on the underlying technology to reliably support survivability of the underlying networks and physical facilities (Kunreuther and LernerLam 2002; Mork 2002). The fact that there were major failures of the basic technology and loss of the command center for 48 hours in the 9/11 event has made this an understandable result. The very workable commercial paging and digital mail systems supplied immediately afterwards by commercial firms (Michaels 2001; Vatis 2002) to the emergency response workers demonstrated that the correction of underlying technology is largely a process of setting integration standards and deciding to spend the necessary funds to update antiquated systems. …

The Design of a Dynamic Emergency Response Management Information System (DERMIS)

Matching a raw GPS trajectory to roads on a digital map is often referred to as the Map Matching problem. However, the occurrence of the low-sampling-rate trajectories (e.g. one point per 2 minutes) has brought lots of challenges to existing map matching algorithms. To address this problem, we propose an Interactive Voting-based Map Matching (IVMM) algorithm based on the following three insights: 1) The position context of a GPS point as well as the topological information of road networks, 2) the mutual influence between GPS points (i.e., the matching result of a point references the positions of its neighbors; in turn, when matching its neighbors, the position of this point will also be referenced), and 3) the strength of the mutual influence weighted by the distance between GPS points (i.e., the farther distance is the weaker influence exists). In this approach, we do not only consider the spatial and temporal information of a GPS trajectory but also devise a voting-based strategy to model the weighted mutual influences between GPS points. We evaluate our IVMM algorithm based on a user labeled real trajectory dataset. As a result, the IVMM algorithm outperforms the related method (ST-Matching algorithm).

/pdf/an-interactive-voting-based-map-matching-algorithm-rrjrdn3yq3.pdf

An Interactive-Voting Based Map Matching Algorithm

Geovisualization is both a process for leveraging the data resources to meet scientific and societal needs and a research field that develops visual methods and tools to support a wide array of geospatial data applications. While researchers have made substantial advances in geovisualization over the past decade, many challenges remain. To support real-world knowledge construction and decision making, some of the most important challenges involve distributed geovisualization - that is, enabling geovisualization across software components, devices, people, and places.

/pdf/geovisualization-for-knowledge-construction-and-decision-19w5185nsw.pdf

Geovisualization for knowledge construction and decision support

Most work with geospatial data, whether for scientific analysis, urban and environmental planning, or business decision making is carried out by groups. In contrast, geographic information technologies have been built and assessed only for use by individuals. In this paper we argue that, to support collaboration with geospatial information, specific attention must be given to tools that mediate understanding and support negotiation among participants. In addition, we contend that visual representations have a particularly important role to play as mediators of geocollaborative activities. With these contentions as a starting point, we present a framework for study of visually-enabled collaboration with geospatial information and for development, implementation, and assessment of geoinformation technologies that support that collaboration. The paper concludes with a brief description of two prototype geocollaborative environments that illustrate the use of the framework developed and provide the basis for ...

Developing a conceptual framework for visually-enabled geocollaboration

Geospatial information is critical to effective, collaborative decision-making during emergency management situations; however conventional GIS are not suited for multi-user access and high-level abstract queries. Currently, decision makers do not always have the real time information they need; GIS analysts produce maps at the request of individual decision makers, often leading to overlapping requests with slow delivery times. In order to overcome these limitations, a paradigm shift in interface design for GIS is needed. The research reported upon here attempts to overcome analyst-driven, menu-controlled, keyboard and mouse operated GIS by designing a multimodal, multi-user GIS interface that puts geospatial data directly in the hands of decision makers. A large screen display is used for data visualization, and collaborative, multi-user interactions in emergency management are supported through voice and gesture recognition. Speech and gesture recognition is coupled with a knowledge-based dialogue management system for storing and retrieving geospatial data. This paper describes the first prototype and the insights gained for human-centered multimodal GIS interface design.

Designing a human-centered, multimodal GIS interface to support emergency management

The present invention includes a system and method for automatically extracting the demographic information from images. The system detects the face in an image, locates different components, extracts component features, and then classifies the components to identify the age, gender, or ethnicity of the person(s) in the image. Using components for demographic classification gives better results as compared to currently known techniques. Moreover, the described system and technique can be used to extract demographic information in more robust manner than currently known methods, in environments where high degree of variability in size, shape, color, texture, pose, and occlusion exists. This invention also performs classifier fusion using Data Level fusion and Multi-level classification for fusing results of various component demographic classifiers. Besides use as an automated data collection system wherein given the necessary facial information as the data, the demographic category of the person is determined automatically, the system could also be used for targeting of the advertisements, surveillance, human computer interaction, security enhancements, immersive computer games and improving user interfaces based on demographic information.

Demographic classification using image components

A novel interface system for accessing geospatial data (GeoMIP) has been developed that realizes a user-centered multimodal speech/gesture interface for addressing some of the critical needs in crisis management. In this system we primarily developed vision sensing algorithms, speech integration, multimodality fusion, and rule-based mapping of multimodal user input to GIS database queries. A demo system of this interface has been developed for the Port Authority NJ/NY and is explained here.

Multimodal interface platform for geographical information systems (GeoMIP) in crisis management

Various techniques for effecting knowledge transfer are provided. In one embodiment, knowledge transfer tasks are identified through parsing of one or more repositories comprising project-related artifacts to ascertain tasks that are relevant to a transitioning project participant, and that may be further analyzed to determine whether knowledge transfer is necessary. In a similar vein, knowledge transfer recipients may be identified through similar parsing of the one or more repositories to identify project participants that are relevant to knowledge transfer tasks, with the resulting list of associated project participants narrowed down to selected knowledge transfer recipients according to their respective ability/availability to receive the knowledge transfer. Because these processes can be automated, including the use of an interactive interface, and based on stored artifacts, the subjectivity and variability of prior art techniques may be substantially reduced.

Knowledge transfer in a project environment

Summary form only given. Unlike desktop systems, embedded systems use different user interface technologies; have significantly smaller form factors; use a wide variety of processors; and have very tight constraints on power/energy consumption, user response time, and physical space. With its platform independence and secure execution environment, Java is fast becoming the language of choice for programming embedded systems. In order to extend its use to array based applications from embedded image and video processing, Java programmers need to employ several optimizations. Unfortunately, due to its precise exception mechanism and bytecode distribution form, it is not generally possible to use classical loop based optimization techniques for array based embedded Java applications. Observing this, this paper proposes a dynamic memory layout optimization strategy for Java applications. The strategy is based on observing the cache behavior dynamically and transforming memory layouts of arrays, when necessary, during the course of execution. This is in contrast to many previously proposed memory layout optimization strategies, which are static in nature (i.e., they are applied at compile time). Our results indicate large performance improvements on a suite of seven array based applications.

Pyush Agrawal

Papers

Designing a human-centered, multimodal GIS interface to support emergency management

Demographic classification using image components

Multimodal interface platform for geographical information systems (GeoMIP) in crisis management

Knowledge transfer in a project environment

Improving memory performance of embedded Java applications by dynamic layout modifications