Visual analytics – Valcri

White Paper WP-2017-011: Applying Visual Interactive Dimensionality Reduction to Criminal Intelligence Analysis

Ms Haider — Fri, 13 Jan 2017 11:04:45 +0000

VALCRI provides a challenging and overwhelming high-dimensional dataset that comprises of hundreds of extracted semantic features in addition to the usual spatiotemporal information or metadata. To overcome the curse of dimensionality and to generate low-dimensional representations of these semantic features we apply interactive high-dimensional data analysis techniques with the goal of obtaining clusters of similar crime reports. However, it is still a challenge for crime analysts to make sense of the results and to provide useful interactive feedback to the system. Therefore, we provide several tightly integrated interactive visualizations that allow the analysts to identify clusters of similar crimes from different perspectives and interactively focus their analysis on features or crime records of particular interest.

Keywords

Criminal Intelligence, High-Dimensional Data Analysis, Feature Extraction, Dimensionality Reduction, Visual Analytics

VALCRI WHITE PAPER SERIES

VALCRI-WP-2017-011 Interactive Visual Dimension Reduction

White Paper WP-2017-010: Roadmap for the Operationalization of Legal and Privacy Requirements in VALCRI Analysis

Ms Haider — Fri, 13 Jan 2017 11:03:35 +0000

This White Paper seeks to illustrate how the LEP guidelines and several legal requirements are set to be further operationalized in the VALCRI project. Based on VALCRI’s data management policy for the live data tests of February 2017, it formulates technical solutions and concrete measures to meet legal data protection requirements adapted to the working environment of criminal analysts.

Keywords

Visual Analytics, Criminal Intelligence Analysis LEP Guidelines, Crime, Analytics, Data Management, Data Protection Principles, Operationalization.

VALCRI WHITE PAPER SERIES

VALCRI-WP-2017-010 Operationalisation Legal

White Paper WP-2017-009: Analytical Provenance for Criminal Intelligence Analysis

Ms Haider — Fri, 13 Jan 2017 09:55:44 +0000

In criminal intelligence analysis to complement the information entailed and to enhance the transparency of the operations, it demands logs of the individual processing activities within an automated processing system. Management and tracing of such security sensitive analytical information flow originated from tightly coupled visualizations into visual analytic system for criminal intelligence that triggers huge amount of analytical information on a single click, involves design and development challenges. To lead to a believable story by using scientific methods, reasoning for getting explicit knowledge of series of events, sequences and time surrounding interrelationships with available relevant information by using human perception, cognition, reasoning with database operations and computational methods, an analytic visual judgmental support is obvious for criminal intelligence. Our research outlines the requirements and development challenges of such system as well as proposes a generic way of capturing different complex visual analytical states and processes known as analytic provenance. The proposed technique has been tested into a large heterogeneous event-driven visual analytic modular analyst’s user interface (AUI) of the project VALCRI (Visual Analytics for Sensemaking in Criminal Intelligence) and evaluated by the police intelligence analysts through it’s visual state capturing and retracing interfaces. We have conducted several prototype evaluation sessions with the groups of end-users (police intelligence analysts) and found very positive feedback. Our approach provides a generic support for visual judgmental process into a large complex event-driven AUI system for criminal intelligence analysis.

Keywords

Analytic Provenance, Visual Analytics, Transparency, Visualization Design, Sensemaking.

VALCRI WHITE PAPER SERIES

VALCRI-WP-2017-009 Provenance

White Paper WP-2017-001: Architecture, Development and Testing Environment for a Visual Analytics-based Criminal Intelligence Analysis System

Ms Haider — Sun, 08 Jan 2017 08:58:28 +0000

The VALCRI architecture is built from different Docker containers that speak with each other using mostly REST interfaces. The architecture is designed to incorporating Security, Ethics, Privacy and Legal (SEPL) solutions. The data stores – the Unstructured Database (UDB) and the Structured database (SDB) – used are controlled by SEPL Enforcement components and a Template Engine manages the previously checked and accepted query templates that can be sent to the data stores. The Advanced User Interface (AUI) server is also designed with SEPL in mind: a Jetty (Java HTTP server and Java Servlet container) instance is created per user by a Jetty Lifecycle Management component. Each such instance lives inside a Docker container to promote isolation. The Jetty instance hosts the mid-tier services, serves the front-end JavaScript code and manages the communication between the mid-tier services and the front-end. The midtier services are written in java and front-end components are implemented using GWT – Google Web Toolkit. The Model View Presenter (MVP) design pattern is implemented. The SEPL Enforcement components, as well as the analysis components, and the Jetty Containers communicate to the CAS (Central Authentication Service) component to ensure that only authorized users can perform certain actions and allows data to be properly restricted. The user management of the CAS component is linked with the LDAP (Lightweight Directory Access Protocol) component to manage and authenticate user credentials. All the components may use the interface exposed by the GrayLog component, ensuring that any action done by any component can be logged in the logging storage. Systematic system integration is a key principle for the success of VALCRI and for that a development pipeline was designed. This pipeline aims to provide continuous system integration while promoting collaboration, contributions, quick feedback to contributions, changing and evolving interfaces, and above all respecting the principle of “keep it working” – allowing to introduce many contributions in small steps while the system continues to compile and work. The GIT Source Control Management (SCM) platform is used for keeping track of changes in the source code. It is accompanied by a GitLab installation that provides a user interface that allows managing the user accounts and the individual code repositories. In order to compile and build the code available from the SCM, a custom build system was developed using Gradle. The Gradle setup is also accompanied with a Nexus component – an artefact repository – which hosts all the compiled, binary VALCRI system components. For each change in the SCM, the source code is automatically rebuilt and all tests are run. In order to do this, a Jenkins installation was put into place. Because the VALCRI architecture includes many services working on different environments, Docker was selected to allow building, shipping and running the complete environments.

Keywords

Visual Analytics, Sense-Making, Criminal Intelligence Analysis, Architecture, REST, Security, Ethics, Privacy and Legal (SEPL), Model View Presenter, Isolation, Google Web Toolkit (GWT), Errai, Docker containers, Central Authentication Service (CAS), LDAP, GrayLog, GIT, Gradle, Nexus, Jenkins

VALCRI WHITE PAPER SERIES

VALCRI-WP-2017-001 Architecture

Visual Interaction with Dimensionality Reduction: A Structured Literature Analysis.

Ms Haider — Wed, 28 Sep 2016 08:44:25 +0000

D. Sacha, L. Zhang, M. Sedlmair, J. A. Lee, J. Peltonen, D. Weiskopf, S. C. North and D. A. Keim. Visual Interaction with Dimensionality Reduction: A Structured Literature Analysis.
IEEE Transactions on Visualization and Computer Graphics (Proceedings of the Visual Analytics Science and Technology), DOI: 10.1109/TVCG.2016.2598495, 2016.

URL: https://ieeexplore.ieee.org/document/7536217/

Keywords: dimensionality reduction, Interactive visualization, machine learning, visual analytics

The Role of Uncertainty, Awareness, and Trust in Visual Analytics

valcriTeam — Mon, 19 Oct 2015 16:52:23 +0000

D. Sacha, H. Senaratne, B. C. Kwon, G. Ellis, and D. A. Keim, “The Role of Uncertainty, Awareness, and Trust in Visual Analytics,” IEEE Transactions on Visualization and Computer Graphics, vol. 22, no. 1, pp. 240–249, Jan. 2016.

Abstract:

Visual Analytics supports humans in generating knowledge from large and often complex datasets. Evidence is collected, collated and cross-linked with our existing knowledge. In the process, a myriad of analytical and visualisation techniques are employed to generate a visual representation of the data. These often introduce their own uncertainties, in addition to the ones inherent in the data, and these propagated and compounded uncertainties can result in impaired decision making. The user’s confidence or trust in the results depends on the extent of user’s awareness of the underlying uncertainties generated on the system side. This paper unpacks the uncertainties that propagate through visual analytics systems, illustrates how human’s perceptual and cognitive biases influence the user’s awareness of such uncertainties, and how this affects the user’s trust building. The knowledge generation model for visual analytics is used to provide a terminology and framework to discuss the consequences of these aspects in knowledge construction and though examples, machine uncertainty is compared to human trust measures with provenance. Furthermore, guidelines for the design of uncertainty-aware systems are presented that can aid the user in better decision making.

keywords —Visual Analytics, Knowledge Generation, Uncertainty Measures and Propagation, Trust Building, Human Factors

URL

SchemaLine: timeline visualization for sensemaking

valcriTeam — Wed, 19 Nov 2014 16:43:01 +0000

P. H. Nguyen, K. Xu, R. Walker, B. L. W. Wong, P. H. Nguyen, K. Xu, R. Walker, and B. L. W. Wong, “SchemaLine: timeline visualization for sensemaking,” presented at the 18th International Conference on Information Visualisation (IV),18th International Conference on Information Visualisation (IV), 2014, pp. 225–233.