RESEARCH - the core of our existence.

A Selection of SAIL LABS’ latest Research Papers

Open Source Intelligence in Disaster Management * submitted
EISIC 2012, European Intelligence and Securoty Informatics Conference
Odense, Denmark, August 2012
"In a disaster situation, it is essential to have real-time access to current, up-to-date information. The sources of information vary from traditional text and print-media to audio and video sources. Social media have recently added another dimension of complexity. One of the key-problems of disasters with global relevance is that information is often available in local languages only. This is the background against which experiments were conducted based on the Sail Labs Media Mining System (MM-System).atures such as video analysis, speech transcription and ontology-based search improvements
were combined to provide information which can be passed to analysts and fed into a situation awareness center."

Open Source Intelligence for Traditional- and Social Media Sources * submitted
The 2012 International Conference on Advances in Social Networks Analysis and Mining
Istanbul, Turkey, Agust 2012
"In this paper we describe the Sail Labs Media Mining (MM) System. The MM-System presents a state-of-the-art end-to-end Open-Source-Intelligence (OSINT) system capable of processing vast amounts of data such as typically gathered from open sources in unstructured form and in diverse formats. Audio, video and textual content can be ingested, processed and made available for search and retrieval, analysis and visualization. Processing is performed by a modular set of technologies packaged as components and covering a large variety of formats and languages. The system can serve as a search platform across open, isolated or secured networks and can be used as a tool for situational awareness, information sharing or risk assessment. It allows the integration of multilingual multimedia, textual and social-media content into the analysis process of security relevant affairs and supports the complete range of phases in the OSINT-cycle."

OPEN SOURCE INTELLIGENCE AM BEISPIEL VON KIRAS/MDL, Multimedia Documentation Lab
9. Sicherheitskonferenz Krems 2011
Krems, Austria, October 2011
"Dieses Dokument beschreibt das Multimedia Documentation Lab (MDL), ein System, welches eine große Menge multimedialer Daten, die typischerweise von Open Sources in einer unstrukturierten Form und in verschiedenen Formaten gesammelt werden, in Echtzeit verarbeitet. MDL ist ein Werkzeug für die Lagebild-Erstellung und Risikobewertung. Es erlaubt die Integration von Multimedia-Content in die Analyseprozesse für sicherheitsrelevante Problemstellungen.Dieses Dokument beschreibt das Multimedia Documentation Lab (MDL), ein System, welches eine große Menge multimedialer Daten, die typischerweise von Open Sources in einer unstrukturierten Form und in verschiedenen Formaten gesammelt werden, in Echtzeit verarbeitet. MDL ist ein Werkzeug für die Lagebild-Erstellung und Risikobewertung. Es erlaubt die Integration von Multimedia-Content in die Analyseprozesse für sicherheitsrelevante Problemstellungen."

Event-Driven Architecture for Health Event Detection from Multiple Sources
MIE 2011, Medical Informatics Europe
Oslo, Norway, August 2011
"Early detection of potential health threats is crucial for taking actions in time. It is unclear in which information source an event is reported first and, information from various sources can be complementing. Thus, it is important to search for information in a very broad range of sources. Furthermore, real-time processing is necessary to deal with the huge amounts of incoming data in time. Event-driven architectures are designed to address such challenges. This will be shown in this paper by presenting the architecture of a public health surveillance system that follows this style. Starting from concrete user requirements and scenarios, we introduce the architecture with its components for content collection, data analysis and integration. The system will allow for the monitoring of events in real-time as well as retrospectively."

Speechless: A Highly Usable Tool for Semi Automated Transcription Correction and Classification
IEEE International Conference on Acoustics, Speech and Signal Processing
Prague, May 2011
"Automatic speech recognition is not perfect. There will always be a certain amount of recognition errors involved; be it because of individual dialects, speaking style, seasonal buzz words or background noise. To ensure an accurate transcript, manual correction is necessary. With Speechless, correction times are as low as 4 times of the media length, while traditional transcription at Sail Labs Technology takes a trained user about 10 times as long. To provide for a continuous improvement of the transcribing system, a concept of classifying and correcting errors in a transcript was needed. The desired software should be designed as an option for manual classification and correction of errors in the transcript. The general requirements were a faster correction speed, the possibility of classifying errors in the transcript and an interface which is easy to use."

Multimedia Documentation Lab
10th International Conference on Knowledge Management and Knowledge Technologies
Graz, Austria, September 2010
"In this paper we describe the Multimedia Documentation Lab (MDL1), a system which is capable of processing vast amounts of data typically gathered from open sources in unstructured form and in diverse formats. A sequence of processing steps analyzing the audio, video and textual content of the input is carried out. The resulting output is made available for search and retrieval, analysis and visualization on a next generation media server. The system can serve as a search platform across open, closed or secured networks. MDL can be used as a tool for situational awareness, information sharing or risk assessment, allowing the integration of multimedia content into the analysis process of security relevant affairs."