What is the Field Lab?

Welcome to our technology field lab. This is a place for early adopters, technical partners and contributors to participate in the creation of technologies InSTEDD is working on.

We have named our lab a ‘Field Lab’ to remind ourselves that InSTEDD is not sitting back and designing in a perfect world. The people who use our technology face complex challenges: extremes of temperature, weather, transportation, exhaustion and information overload. Our work will be useful only as long as we stay closely connected to real world conditions.

Are you looking for things that have gone beyond an experimental stage? Once we’ve tested a Field Lab project and know it’s mission-ready, we mark it as Ready for Use. Below is a list of project in process at the Field Lab. We invite you to learn, download, tinker, play and most importantly, engage with us as part of our community. You can send comments directly to Ed Jezierski (VP, Engineering), Robert Kirkpatrick (CTO) or Eric Rasmussen (CEO) by using lastname@instedd.org.

InSTEDD GeoChat

GeoChat
 
How to get everyone on the same page, and keep them there?
 
When a major humanitarian crisis occurs, every second matters for the affected community. People may be trapped, injured, or sick, and the longer it takes responders to reach them, the poorer the outcome is likely to be. What is needed is a response that is agile, efficient, and effective, where diverse groups – NGOs, the UN, national governments, military, and the local community – self-organize temporarily into a coherent, coordinated whole to provide assistance to a population in need.   Unfortunately, more often than not, coordination among relief organizations today is far from adequate. Responders in the field find it difficult to keep one another in the loop about what they are doing and where. They have a constant sense that they out of touch with headquarters, and headquarters with them.  Often, they lack adequate means to engage members of the local community and ensure that they participate meaningfully in the response. When key contacts are excluded from the process, they are left with an incomplete understanding of what is needed, and they cannot act as one. Delays mount up, too little arrives too late, and the cost may be measured in human lives.
 
There are many factors that may contribute to this lack of coordination, but to a great degree, much of it comes down to a single problem: reliable team-based communication during and after a crisis is critical to success, yet remarkably difficult to achieve. Effective humanitarian action is like a team sport, where scoring a goal depends on everyone’s understanding the plan and communicating well enough to improvise when plans change. In a crisis, responders must first establish reliable cross-organizational flows of information that include everyone with a role to play, and then interact regularly with one another to maintain a shared understanding of current plans, new developments, and who is doing what where. Yet as dozens, or even hundreds, of relief organizations mobilize teams to respond, arrive on site, and join forces to coordinate relief efforts, they often find that the technologies they use to communicate internally – computers, telephones, and radios -- do not allow them to communicate effectively with all of their new teammates. Inevitably, someone is left out of the circle of communication and, at a critical moment, fails to anticipate when it is their turn to act. 
 
Make sure everyone can participate, with any device, over any network
 
It is widely recognized that communication in post-crisis environments is difficult. Communications infrastructure may not be adequate, relief workers are hot, tired, and scared, and everyone arrives with whatever tools they happen to have. What is not as widely recognized is that the user of a team-based communication tool is not an individual, but a group.  Either everyone can participate in conversation, or the tool has failed to meet the need– it’s all or none.  If key team members are excluded, the rest of team may be left with a tough choice: try to make it work without them, or revert to inefficient, non-technical approaches such as daily face-to-face meetings.  Unfortunately, it’s a choice they face often, from one crisis to the next.  The latest web-based collaboration tool only works if all team members have access to computers and the Internet.  Field radios are useful for team coordination, but only if 1) everyone on the team has a radio, 2) everyone stays in range, and 3) all of the radios can interoperate. Phone-based conference calls are expensive, and during the response phase, telephony networks may be damaged or so overloaded by those attempting to reach loved ones that it’s difficult to place a call. Whether for lack of Internet access, hardware, cost, interoperability, or network capacity, crisis communications technologies in use today often fail to   meet the needs of the team by failing to include one or more members in the flow of critical information.
 
 
GeoChat:  Emergent Group Communication at the Edge of the Network
 
GeoChat is a flexible open source group communications technology that lets team members interact to maintain shared geospatial awareness of who is doing what where -- over any device, on any platform, over any network. GeoChat allows you and your team to stay in touch one another in a variety of ways: over SMS, over email, and on the surface of a map in a web browser.   Whether you are sitting at a computer with a high-speed Internet connection, or on the go with your mobile phone, GeoChat let you react to events on the ground with maximum agility, forming cross-organizational virtual teams on the fly, linking field to headquarters, and keeping everyone on your team connected, in sync, and aware of who is doing what, and where.
 
 
How GeoChat Works:
  • Register with GeoChat either online, by email, or by SMS
  • Create a new GeoChat group and invite your friends
  • Send messages to one another, or share them with the entire group.
  • If you’re mobile using your cell phone, prefix a text message with your location -- say your current address, or a latitude and longitude from a GPS - and GeoChat will place your icon on the map for online users to see. 
  • If you’re online in the browser, select a teammate’s icon on the map, click reply, and send a reply back to them over SMS.
Features: 
  • Create, join and participate in chat groups by SMS, email, or web browser.
  • Translates location names sent by users to a position on a map
  • Supports a variety of explicit location formats, as well as other user-defined tags.
  • Subscribe a group to one or more RSS/ATOM feeds, and each new item will be broadcast to mobile users via SMS.
  • Groups may be set as public or private.
  • GeoChat Server is available both as a free download and as a hosted service.
  • Twitter access via “geochat”, and domestic US gateway service via 44911.
  • Dedicated international SMS gateway supported by 96% of the world’s mobile carriers.  
  • Optional “local gateway” mini-client that allows you to plug a local cell phone into your laptop, connect to the Internet, and allow users to send and receive text messages through the service via the local cell network, rather than using the international gateway.
Benefits:
  • Let’s you see, at a glance, who said what, when, and where.
  • Allows geospatial ground-truthing, as your mobile team works to confirm, refute, or update data on your map.
  • Allows mobile users to verify, refute, or update information live from the field
  • Allows highly-connected users to share the benefits of their geospatial “big picture” view and push out relevant RSS/ATOMfeeds to a barely connected users via SMS.
  • Ensure that your teammates know where you are and what you are doing.
  • Visualize your remote team on the surface of a map and interact with them.
  • Works on any PC, Mac, or Linux PC capable of running Mozilla Firefox
  • Works using any cell phone capable of sending and receiving SMS messages.

 For Developers:
  • Source is available under the GPLv3 license.

 GeoChat Infrastructure

Current Status: 

GeoChat is in Beta  Contact info@instedd.org if you are interested in participating. (Participating in the beta means you get a little bit more suppport from our team)

GeoChat is in use for rapid response teams in Thailand and Cambodia, spanning provincial to sub-district health officers and volunteers.

InSTEDD Riff

What is Riff?

Over the last decade, the majority of the designs, analyses and evaluations of early detection (or biosurveillance) systems have been geared towards specific data sources and detection algorithms. Much less effort has been focused on how these systems will "interact" with humans. For example, consider multiple domain experts working at different levels across different organizations in an environment where numerous biosurveillance algorithms may provide contradictory interpretations of ongoing events. Riff enables detection, prediction and response to health-related events (such as disease outbreaks or pandemics) through a collaborative environment that combines data exploration, integration, search and inferencing – providing more complex analysis and deeper insight.

Although development of Riff has initially been focused on health-related detection scenarios, the underlying system is a general collaboration environment for content creation, social metadata annotation, and automated analysis with potential applicability in a wide range of areas.  Several organizations are exploring the use of Riff in areas as wide ranging as humanitarian crisis reporting and conflict early warning.  One organization, for example, has recently begun training Riff's integrated SVM machine learning engine to identify hate speech and other potential indicators of geopolitical deterioration in news reports.

Features:

  • Create collaborative workspaces, invite colleagues, subscribe to data sources you choose to monitor
  • Interact securely with your team to sift through the data stream for emerging events
  • Annotate items with tags, comments, ratings, links, locations, files, alerts, and other social metadata
  • Autonomous agents perform data fusion, feature extraction, classification, tagging,  geo-coding
  • Integrated hypothesis formation, visualization, machine learning

How does Evolve work?

Evolve consists of several high-level modules, including: 1) Data aggregation and gathering, 2) Automatic feature extraction, data classification and tagging, 3) Human input, hypotheses generation and review, 4) Predictions and alerts output, and 5) Field confirmation and feedback.

  1. The data aggregation and gathering module allows users to collect (or extract, transform and load (ETL) information from several sources (SMS messages (e.g., GeoChat), RSS feeds, email list (e.g., ProMED, Veratect, HealthMap, Biocaster, EpiSpider), OpenROSA, Map Sync, Epi Info™, documents, web pages, electronic medical records (e.g., OpenMRS), animal disease data (e.g., OIE, AVRI hotline), environmental feed, NASA remote sensing, etc.).
  2. The automatic feature extraction, data classification and tagging module is an architecturally extensible module that allows the introduction of machine learning algorithms (e.g., Bayesian, SVM). These components extract and augment the features (tags or metadata) from multiple data streams; such as: source and target geo-location, time, route of transmission (e.g., person-to-person, waterborne), etc. In addition, these components help detect relationships between these extracted features within a collaborative space or across different collaborative spaces. Furthermore, with human input, these components can suggest possible events or event types (e.g., at the earliest stages of a disease outbreak: “there is an unknown respiratory event, transmitted person-to-person, detected in location X, and with a certain spatio-temporal pattern”).
  3. The human input and review module is exposed as a set of functionalities that allows users to comment, tag, and semantically rank the elements (positive, neutral, or negative). Additionally, users can generate and test multiple hypotheses in parallel, further collect and rank sets of related items (evidence), and model against baseline information (for cyclical or known events). The system maintains a list of ongoing possible threats allowing domain experts to focus their field information and either confirm or reject the hypotheses created. That feedback is then fed into the system to update (increase or decrease) the reliability of the sources and credibility of the users in light of their inferences or decisions.

Benefits:

  • Detect emerging critical events sooner and enable your team to take the right action earlier.
  • Allow human experts and autonomous agent-based analytic services to augment one another’s efforts.
  • Pattern detection algorithms learn from past events – and your team’s characterization of them – to improve performance the next time around.
  • Fully extensible open source solution allows you to incorporate your own data sources, services, and embedded modules.

Results

In the Public Health and Biosurveillance domain, Riff helps synthesize health-related event indicators from a wide variety of information sources (structured and unstructured) into a consolidated picture for analysis, maintenance of “community-wide coherence”, and collaboration. Current automatic classification includes seven syndromes, ten transmission modes, more than 100 infectious diseases, 180 microorganisms, 140 symptoms, and more than 50 chemicals. Presently, Riff is being piloted in the Mekong Basin region of Southeast Asia.

A(H1N1) Pandemic Collaborative Workspace using Riff

 

Related Links:

 

Project Lead:

Taha Kass-Hout, MD, MS
Advisor, Global Public Health and Informatics
Taha's Blog

 

Current Status: 

Riff is currently in limited, closed beta testing with selected organizations. If you are interested in using Riff or other InSTEDD technologies, please contact us at info@instedd.org.