Applying Knowledge-Based Reasoning for Information Fusion in Intelligence, Surveillance, and Reconnaissance

Kuwertz, Achim; Mühlenberg, Dirk; Sander, Jennifer; Müller, Wilmuth

doi:10.1007/978-3-319-90509-9_7

Cited by 9 publications

(4 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It supports operational processes in NATO Joint ISR and by using the Intelligence Cycle. In [16], the author presented elements to achieve integration of information (information fusion). The solution includes a distributed surveillance system and intelligence databases.…”

Section: The Literature Reviewmentioning

confidence: 99%

ISR Data Processing in Military Operations

Buřita¹,

Novak²

2020

Adv. sci. technol. eng. syst. j.

View full text Add to dashboard Cite

This paper provides an overview of Intelligence, Surveillance, and Reconnaissance (ISR) data with respect on NATO standards and recommendations; further presents methods, tools, and experiences in ISR data processing in military operations. The steps of the Intelligence cycle and disciplines Business Intelligence (BI), Data Warehousing, Data Mining, and Big Data are presented in the introduction. The literature review is oriented to the analysis of intersections between ISR and BI methods. The next chapter describes the ISR data processing in detail; there are listed structures, formats, standards, and data from the operational point of view. The ISR operational picture is explained, and steps of the ISR data mart is completed. The last part is oriented to Big Data processing; NoSQL, inmemory and streaming databases. The last two chapters are focused on the description of research results in the processing of ISR data. The ISR data mart experiment processes the radio transmission data that consists of detected radio signals. Results are visualized in RapidMiner Studio. The Big Data experiment is realized in Apache Hadoop.

show abstract

Section: The Literature Reviewmentioning

confidence: 99%

ISR Data Processing in Military Operations

Buřita¹,

Novak²

2020

Adv. sci. technol. eng. syst. j.

View full text Add to dashboard Cite

show abstract

“…To perform this operation one has to decide if this instance is a new one and should be associated (data association) correctly with its context in the model or if it already exists somewhere in the model and some values (attributes) of the instance have to be updated. In the latter case, we have an information fusion problem, where certain values are updated according to actual observations [29]. Both problems can be tackled using a semantic world model [29] for managing the information in the knowledge base.…”

Section: Mapping Of Amr To Domain Modelmentioning

confidence: 99%

“…In the latter case, we have an information fusion problem, where certain values are updated according to actual observations [29]. Both problems can be tackled using a semantic world model [29] for managing the information in the knowledge base.…”

Section: Mapping Of Amr To Domain Modelmentioning

confidence: 99%

Towards information extraction from ISR reports for decision support using a two-stage learning-based approach

Mühlenberg

Kuwertz

Schenkel

et al. 2019

Open Architecture/Open Business Model Net-Centric Systems and Defense Transformation 2019

View full text Add to dashboard Cite

The main challenge of computer linguistics is to represent the meaning of text in a computer model. Statistics based methods with manually created features have been used for more than 30 years with a divide and conquer approach to mark interesting features in free text. Around 2010, deep learning concepts found their way into the text-understanding research community. Deep learning is very attractive and easy to apply but needs massive pools of annotated and high quality data from every target domain, which is generally not available especially for the military domain. When changing the application domain one needs additional or new data to adopt the language models to the new domain. To overcome the everlasting "data problem" we chose a novel two-step approach by first using formal representations of the meaning and then applying a rule-based mapping to the target domain. As an intermediate language representation, we used abstract meaning representation (AMR) and trained a general base model. This base model was then trained with additional data from the intended domains (transfer learning) evaluating the quality of the parser with a stepwise approach in which we measured the parser performance against the amount of training data. This approach answered the question of how much data we need to get the required quality when changing an application domain. The mapping of the meaning representation to the target domain model gave us more control over specifics of the domain, which are not generally representable by a machine learning approach with self-learned feature vectors.

show abstract

“…Together with a common semantics, relevant information can easily and correctly be located and extracted for further purposes. 15 At formal reporting, metadata can get incorporated into the formal reports themselves which is very favorable with regard to data and information management, especially also with regard to accompanying data/ information quality management ¶ . Incorporating the metadata into the formal reports themselves can avoid inconsistencies between the reports and the metadata.…”

Section: What and Whymentioning

confidence: 99%

Formal reporting for information exploitation and dissemination in Joint ISR

Sander

Essendorfer

Dyck

et al. 2019

Open Architecture/Open Business Model Net-Centric Systems and Defense Transformation 2019

Self Cite

View full text Add to dashboard Cite

In complex operational scenarios where multiple nations and forces cooperate, flexible System of Systems (SoS) architectures being customizable to specific operations are needed. Relevant operational processes as defined within Joint ISR (Intelligence, Surveillance and Reconnaissance) and the Intelligence Cycle need to be supported. To maximize efficiency and effectiveness of Joint ISR capabilities, each Joint ISR result needs to answer the corresponding information requirement accurately. Commanders must receive the relevant information in a condensed, well-prepared manner instead of being overflowed with large amounts of (raw) data. Ensuring a common understanding of each exchanged piece of information within the defence coalition is also of utmost importance. Architectures supporting these requirements need to make use of relevant standards and agreements for data/ information management. As reports may be provided by all Joint ISR capabilities, the topic of reporting is of high importance, here. Within the described context, our publication deals with formal reporting which can be defined as organizational process at which relevant information is provided as formal reports, i.e., as documents being structured according to pre-defined (agreed) rules. We present means for ensuring allied interoperability and further (semi-)automatic processability of the information being contained in formal reports by technical means and under consideration of the relevant doctrines and standards. We also address specific means needed to ensure the creation of formal reports of high quality. Finally, we discuss current issues and new requirements on formal reporting which have to be still addressed in the field of Joint ISR.

show abstract

Applying Knowledge-Based Reasoning for Information Fusion in Intelligence, Surveillance, and Reconnaissance

Cited by 9 publications

References 14 publications

ISR Data Processing in Military Operations

ISR Data Processing in Military Operations

Towards information extraction from ISR reports for decision support using a two-stage learning-based approach

Formal reporting for information exploitation and dissemination in Joint ISR

Contact Info

Product

Resources

About