Interlink Systems science Inc.

Lake Success, NY, United States

Interlink Systems science Inc.

Lake Success, NY, United States
SEARCH FILTERS
Time filter
Source Type

Kadar I.,Interlink Systems science Inc.
Proceedings of SPIE - The International Society for Optical Engineering | Year: 2012

• Questions and Comments? • There are many issues and challenges remaining requiring research, implementation, testing to validate the proposed methods. - However, PRM-based models have been shown to converge faster to a solution, than non-cognitive models. Therefore, the PRM model is expected to perform well, and can also be used in many other apps. Addressed: • Definition of Intent • The role of Intent in Situation Assessment • Models of Intent • The need for Cognitive Models of Intent - Issues and Challenges • The Importance of Information Exchange as Input to Cognitive Models, viz., Perceptual Reasoning Machine (PRM) • Social Networking Sites providing information exchange • Type of Social Networking Sites • The role of Twitter - "Twitterology" inputs derived for use in PRM • The Generic Information Process Model via PRM • The Cognitive Perceptual Reasoning Machine Paradigm Information Flow. © 2012 Copyright Society of Photo-Optical Instrumentation Engineers (SPIE).


Kadar I.,Interlink Systems science Inc.
Proceedings of SPIE - The International Society for Optical Engineering | Year: 2011

The purpose of this position paper, along with the accompanying viewgraphs, is to highlight an essential component of Hard and Soft Fusion, stated in the title, which is associated with the salient problems identified in introductory statement for the "Invited Panel Discussion on Real-World Issues and Challenges in Hard and Soft Fusion": "The panel will address salient real-world issues and challenges in hard and soft data fusion illuminated by invited experts. Accurate situation assessment [1-4] sometimes cannot be accomplished using just hard or soft data sources alone. Specifically sources of "hard information" are physics-based sources that provide sensor observables such as radar or video data, while "soft information" is usually provided by human-based sources [5, 6]. Fusion of hard and soft data can provide situation pictures that are better than those using hard or soft data alone. For example, patrol reports provide soft data in addition to hard data from physical sensors in urban operational environments. While algorithms for fusing information from physical sensors has a substantial development history as well as maturity [7-14], complex technical issues remain in the representation of human-based information [6] to make it suitable for combining with sensor based information. Conceptual real-world related examples associated with the overall complex problem will be addressed by the panel to highlight issues and challenges. Audience participation is welcomed to provide a forum for exchange of ideas". © 2011 SPIE.


Yang C.,Sigtem Technology, Inc. | Kadar I.,Interlink Systems science Inc. | Blasch E.,Air Force Research Lab | Bakich M.,Air Force Research Lab
Proceedings of SPIE - The International Society for Optical Engineering | Year: 2011

In this paper, we compare the information-theoretic metrics of the Kullback-Leibler (K-L) and Renyi (α) divergence formulations for sensor management. Information-theoretic metrics have been well suited for sensor management as they afford comparisons between distributions resulting from different types of sensors under different actions. The difference in distributions can also be measured as entropy formulations to discern the communication channel capacity (i.e., Shannon limit). In this paper, we formulate a sensor management scenario for target tracking and compare various metrics for performance evaluation as a function of the design parameter (α) so as to determine which measures might be appropriate for sensor management given the dynamics of the scenario and design parameter. © 2011 SPIE.


Kadar I.,Interlink Systems science Inc.
Proceedings of SPIE - The International Society for Optical Engineering | Year: 2014

Issues, challenges, cause and effect and the domain of CE were described. The importance of a systems level defensive approach in CE coupled with fusion applications selection were identified. In Cyberspace aiding of analyst's end-user cognitive functions were highlighted. Specific domains of defenses addressed include: (1) A Cyber Information Processing System for DOI Defense and Data Analysis; (2) Cyber DOI Defense: Analyst Cognition Modeling in OODA Loop, and its Relationship to user Data Fusion Information Group (DFIG) Model; (3) Challenges of Contested Collaboration in Hard and Soft Information Fusion; (4) Mobile Agents-Based Incremental Data Fusion in Jammed UGS/WSNs; (5) Importance of Peer-to-Peer (P2) Networks vs. Client Server in C2/BM/ISR; (6) Example of a highly successful operational NCW C2/BM/ISR P2P Networked Anti-Jam System in Contested Environments: "Cooperative Engagement Capability" employing measurements domain fusion.


Blasch E.,Air Force Research Lab | Yang C.,Sigtem Technology, Inc. | Kadar I.,Interlink Systems science Inc.
Proceedings of SPIE - The International Society for Optical Engineering | Year: 2014

Over the last two decades, many solutions have arisen to combine target tracking estimation with classification methods. Target tracking includes developments from linear to non-linear and Gaussian to non-Gaussian processing. Pattern recognition includes detection, classification, recognition, and identification methods. Integrating tracking and pattern recognition has resulted in numerous approaches and this paper seeks to organize the various approaches. We discuss the terminology so as to have a common framework for various standards such as the NATO STANAG 4162 - Identification Data Combining Process. In a use case, we provide a comparative example highlighting that location information (as an example) with additional mission objectives from geographical, human, social, cultural, and behavioral modeling is needed to determine identification as classification alone does not allow determining identification or intent. © 2014 SPIE.


Cui B.,Rochester Institute of Technology | Yang S.J.,Rochester Institute of Technology | Kadar I.,Interlink Systems science Inc.
Proceedings of SPIE - The International Society for Optical Engineering | Year: 2013

Predictive analytics in situation awareness requires an element to comprehend and anticipate potential adversary activities that might occur in the future. Most work in high level fusion or predictive analytics utilizes machine learning, pattern mining, Bayesian inference, and decision tree techniques1, 2 to predict future actions or states. The emergence of social computing in broader contexts has drawn interests in bringing the hypotheses and techniques from social theory to algorithmic and computational settings for predictive analytics. This paper aims at answering the question on how inuence and attitude (some interpreted such as intent) of adversarial actors can be formulated and computed algorithmically, as a higher level fusion process to provide predictions of future actions. © 2013 SPIE.


Hintz K.,George Mason University | Kadar I.,Interlink Systems science Inc.
FUSION 2016 - 19th International Conference on Information Fusion, Proceedings | Year: 2016

The concept of goal lattices has been presented as a method with which to determine the mission value of each admissible sensor action as an aid in computing the associated expected information value rate. Implicit collaboration of sensing platforms has previously been presented as a method for coordinating the actions of autonomous entities with shared goals. In this paper we formally define that interaction and show how joint mission goals common to collaborating agents can be used to evaluate admissible sensing actions. The net result of incorporating joint goals is expected to reduce the amount of redundant sensing actions when compared to autonomous sensing systems operating without joint, collaborating goals. © 2016 ISIF.


Kadar I.,Interlink Systems science Inc. | Hintz K.,George Mason University
FUSION 2016 - 19th International Conference on Information Fusion, Proceedings | Year: 2016

We introduce the method of the Maximum Entropy (MaxEnt) model for fusing local decisions in a distributed multiple sensor system. The fusion center receives local binary decisions in the usual parallel architecture. No assumptions are made about knowing any local decision rules. Our approach is based on the concept of machine learning, wherein the MaxEnt parametric model is used for supervised classification and prediction serving as the central (global) decision rule. Therefore, the system is able to learn the detection performance of the sensors as a function of time without prior knowledge of the actual probabilities of local decisions, only requiring an initial set of random training data. Thus it is demonstrated that the system is adaptive and can learn contextual changes of the sensors. Furthermore, we provide simulation results comparing the MaxEnt fusion center performance with published results using both the Bayesian formulation and Neyman-Pearson criterion and with MaxEnt achieving the best, realistic detection performance demonstrating the effectiveness of the method. © 2016 ISIF.


Hintz K.,George Mason University | Kadar I.,Interlink Systems science Inc.
2015 18th International Conference on Information Fusion, Fusion 2015 | Year: 2015

We depict the functions and extension of a novel information theory based sensors management (ISBM) system to information based sensor and mission management (IBSMM) such that intelligence collection is effective in an expected value sense while remaining independent of any particular platform, sensor or point solution. We describe the proposed implementation via implicit collaboration through common mission goals. Integral to this concept is utilizing the scope of knowledge at each sensing resource in order to provide context sensitive information extraction from sensor data via context-based information fusion. © 2015 IEEE.


Kadar I.,Interlink Systems science Inc
Proceedings of SPIE - The International Society for Optical Engineering | Year: 2015

This succinct position paper, coupled with the associated viewgraphs, is to provide: (1) a short historical background, and recent research efforts and challenges in context definitions, modeling, extraction and use; and (2) most importantly, introduce the fusion community to unexplored research areas and challenges by Big Data Predictive Analytics machine adaptive learning processing methods to predict context, and concept dependent performance information, and detect/identify contextual and concept changes, "concept drifts" (CDs) [1] in enormous volume and speed online data streams information exchange in cyber and fusion systems. The balance of the paper illustrates the evolution of CD, adaptive machine learning, application of context, and concept/context change in hard/soft fusion, cyber and social networking applications along showing analogy between generalized adaptive machine learning, and the PMS/PRM process model system/perceptual reasoning machine scheme [2].

Loading Interlink Systems science Inc. collaborators
Loading Interlink Systems science Inc. collaborators