Note: The information contained is over 20 years old. The document is intended to aid startups seeking to do their first SBIR. We find that knowing what the end product looks like is helpful to getting underway.

Acme (ACME DYNAMITE COMPANY), together with consultants Dr. Speedy Gonzalez and Eric Adolphe, is pleased to submit this proposal to develop a Big Network Reporting (BNR) system in response to the Navy solicitation N091-076, entitled “Translation of Network Metrics to Behavior Attributes.”

The background of our team is particularly appropriate for the task of developing a system to support Marine Corps System Command PM Intel (MCSC PM Intel) objectives. The Principal Investigator, Mr. Road Runner, is an award-winning software developer at ACME DYNAMITE COMPANY with years of experience writing software for knowledge engineering and visualization. Dr. Speedy Gonzalez is an Organizational and Behavioral Scientist with experience in assessing human behaviors, and serves as a Subject Matter Expert. Mr. Wiley Coyote provides significant experience in commercializing SBIR technologies. ACME DYNAMITE COMPANY personnel have developed award-winning software solutions for the Federal Intelligence Community, including software designed for social networking, knowledge engineering, and data fusion.

Social networking sites such as Facebook and MySpace are increasingly popular – MySpace, the most commonly used social networking site, has more than 200 million profiles. A study by Psych Central has found that 54 percent of adolescents frequently discuss high-risk activities including sexual behavior, substance abuse or violence using MySpace.6 With the rise in social networking sites (SNSs) popularity and use, parents and those who work with teens have concerns that these sites might expose teens to ill-intentioned online predators, cyber- bullies and increased peer pressure.

The researchers’ study “Reducing At-Risk Adolescents’ Display of Risk Behavior on a Social Networking Web Site” examined if patterns of behavior may be detected and if early intervention would have a positive impact on reducing online display of such behaviors in the SNS. Looking at 190 self-described 18 to 20-year olds with public MySpace profiles that met study criteria for being at-risk, the profiles received a single intervention email from “Dr. Meg,” the physician online profile, who became a MySpace member. The study found that a single email intervention reduced the potential for violent or at risk behavior by 30 percent. However, the study required manual sifting through profiles, content, and messages to identify interesting patterns.

Another study investigated whether previously documented patterns of gendered behavior on the Internet, such as higher levels of fear and anxiety depressing usage among women, carried over to these new online social locations.2 Analysis of the data revealed gendered patterns of use: for example, women were more likely to use the sites to keep in touch with their existing friends while men were more interested in meeting and networking with new people. While female students reported higher levels of privacy concerns and complained more of unwanted contact, they also posted more pictures of themselves. Female students seemed to try to manage their privacy concerns by restricting access to their profiles: women were twice as likely to restrict their profiles' visibility to only their SNS "friends," compared to men.

The results were especially interesting since fear and anxiety, although they influence self-presentation strategies, do not depress usage, suggesting motivation and availability of access are also important factors in mediating this relationship.

Within the context of MCSC PM Intel requirements, there is a desire to develop technological tools that will provide network metrics to the behavioral understanding of an organization. Additionally, the tool should enable analysts to identify projections of behavioral attributes by calculating traits of nodes within a classic network. These attributes will allow the analyst to identify the future performance of the organization’s social network. With the demonstration of a calculated technological system, the tools should also predict the organization’s future behavioral attributes from a hypothetical stimulus.

Some of the behavioral attributes include ascetic, reclusive, elusiveness, anger, resistance to change, acceptance of inequality, and other indicators that would predict individual social behavioral responses in a changing environment. These attributes do not limit the scope of examination but will serve as a basis to evaluate the overall social environment and its social behaviors within the network. Examination, including an observational study and an analytical streamlined process, will provide for the architecture of the signature vector.

Past and current behavior factors will assist as indicative predictors for the human network node and the social network. A means for best results will be gained by diagnosing the culture of the organization and provide taxonomy of the nodes within the common network. Corporate culture can have a decisive impact on corporate success and profitability. The basic issue is that unless the organization adequately manages its cultural change process, the organization may find itself with a culture that does not support the goals it wants to or needs to achieve.1 Sources to examine this culture will begin with the assessment of the N-dimensions of the network.

Measurement of the various fields will determine the human nodes. Its results will facilitate the development of a prototype application service than can map behavior attributes to network nodes.

Views of this social network analysis will be in terms of nodes and its alignments. The analysis will include a study and diagnostic review of the organization’s culture to determine its relationships in terms of the nodes’ networks. However, it cannot be assumed that the shape of the social network determines the network’s usefulness to its individuals.

The intent of this work is to develop mappings in an N-dimensional human network space to a relevant behavior space. Given the unknown attributes of the objects, there will be a need to provide substitutable alternatives that offer suitable default to a “do-nothing” behavior.

When using this pattern, we will introduce a collaboration that already exists. Some of these instances would be do-nothings while others would be objects to serve as surrogates, for the lack of an object of a given type. Using the collaborator would require the identification of those that actually provide behavior patterns in order to develop behavioral strategies. While analyzing the distinct differences between the collaborator and the do-nothing elements, we will find collaborators that do nothing and treat it the same way we would treat one that actually provides behavior.

In the development of these behavioral strategies, we will first restrict ourselves to controllable behaviors. The set of controllable behaviors will serve to coincide with the do-nothing components in order to create the simplest strategies possible. From these elements, we will arbitrarily choose a pattern of definable behaviors to denote measurable algorithms for the development of a working matrix.

For instance, we envision a strategy pattern to move one element and another separate strategy pattern to control another element. Results would be the creation of suppositions to determine whether all measurable elements are working prior to setting nodes for the taxonomy.

When instituting measurable elements, we will use three objects (abstract, real, and null). The key to this pattern, shown in Figure 1, is that the abstract objects will define the interface for all objects of this type. Relating and interfacing the measurable elements is why the client must identify the collaborators for the abstract object. It will serve as the interface of all classes, as deemed appropriate, for the implementation of default behavior. For the real object, we will use the abstract object to provide useful behavior that the client expects. The null object will conform to the abstract class’s interface so that it can substitute for a real object and provide for the behavior the client is expecting. The number of null objects is dependent on results that determine there is more than one way to do nothing. The proposed system will use the derived metadata to translate human network data to actionable intelligence.

Figure 1: Object-oriented representation for measurable elements. This design shows the system will represent known and unknown values, including them in both the behavioral rules and the nodes in the social network.

Intelligence must be defined by the client as its definition can be ostensibly different based on varying scopes, situations, and environment. Its definition will serve as a base to determine social behaviors within the organization’s structure, its radiality, and structural equivalence.

Understanding the organization’s behavior relies on a significant degree of its identified behavioral attributes. More accurate derivatives will come from the organization’s behavioral assessment, for the development of nodes, and to detect and technically translate desired behavioral models. Modeling is dependent on the organization’s expectations. Its expectations shall set the standard for the structural pattern of its human networks.

The intent of this Phase I SBIR is to research and develop a system that will identify behavior traits of humans within a social network. The network could include organizations, events, locations, or concepts in addition to individuals. The tool will identify or derive metrics from the social network, and use a reasoning system to apply a taxonomy of behavioral rules. The reasoning system will enhance the metadata for each node within the social network.

Ultimately, the system will help to identify the roles of individuals within a social network, and identify attributes such as hostility, influence, or reclusiveness. This system will enable the warfighter to predict how both individuals and organizations will react to external stimuli, and allow analysts to predict the most advantageous course of action when dealing with social networks. Analysts may also use the same system to identify surreptitious behavior that may be indicative of terrorist cells using social networking sites; or precursors to criminal or other anti-social behaviors.

ACME DYNAMITE COMPANY’s subject matter expert, Dr. Speedy Gonzalez, has over 30 years of experience assessing organizational behaviors. She has developed programs to diagnose an organization’s strengths and weaknesses to identify valuable information about the organization. In addition, she has performed individual behavioral assessments in clinical environments. She has served on federal task forces, governmental committees, and corporate boards in both the private and public sectors. She has directly worked with the United States federal government administrations in their federal acquisition programs, human resource management, human factor studies, and its workforce development. Team ACME DYNAMITE COMPANY will incorporate her strong experience with behavioral patterns within organizations as the basis for the rules taxonomy within the BNR system.

ACME DYNAMITE COMPANY’s commercialization consultant, Mr. Wiley Coyote, has successfully developed technology for many SBIRs during his career. He helped to commercialize several technologies developed through SBIR contracts. Mr. Coyote’s Mini-Telecommunications Demarcation System (MTDS) may be found in every civilian air traffic control facility in the United States. Mr. Coyote is a 2007 winner of the Tibbetts Award for SBIRs and is an honoree of the National Inventor’s Hall of Fame. His expert advice provides Team ACME DYNAMITE COMPANY a valuable advantage for exploiting the commercial potential of the BNR system.

The principal investigator, Mr. Road Runner, has developed numerous software systems and prototypes. He is an expert in visualization, knowledge representation, and semantic reasoning. He recently designed a utility for analyzing a social network for the Visual Analytics Science and Technology (TREK) challenge, winning an award for Effective Toolkit Integration. He also developed a library of software for visualization, automated reasoning, and data fusion, and released this software to the Open Source community as the Prajna Project.

ACME DYNAMITE COMPANY, an ISO9001 certified, 8(A) small business, is an Information Technology Solutions company that provides innovative technological services to support Federal Intelligence clients. ACME DYNAMITE COMPANY offers services in the core areas of software engineering, systems engineering, management consulting, and technology integration. Our specialty is delivering comprehensive, best of breed solutions for our customers by leveraging our domain expertise and established partnerships with commercial vendors and strategically aligned service-providers.

ACME DYNAMITE COMPANY has developed, integrated, tested and deployed numerous systems using agile methodologies to ensure that we meet the immediate needs with a level of quality and response that is required by the customer. ACME DYNAMITE COMPANY use of agile methods enables its developers to integrate multiple sources and systems, adjust and respond quickly to customer mission changes, and provide the ability to anticipate problem areas and identify solutions to avoid delays in development and implementation. ACME DYNAMITE COMPANY has included the integration of COTS, GOTS, and FOSS software to satisfy customer requirements.

The BNR system includes several innovative applications of cutting-edge software design. During the data gathering stage, the system will extract relevant information from data sources, including social web sites. While other software already performs some of this extraction, the BNR system will model the available data, and fuse data from different data sources into a cohesive, unified data model. The system can then use this cohesive data model to derive the values for an N-dimensional space of human behavior.

The reasoning engine includes innovative elements within its design. Many systems have created inference engines and rules engines for various types of data.12 However, most of these systems operate on rules that do not include uncertainty. To account for data that may not include all measurable factors and the unpredictability of human behavior, the rules taxonomy will include rules with some degree of uncertainty. Unlike current rules inference engines, the BNR system may apply rules even when the system does not have values for all measurable elements within a social network.

The reasoning engine will process any standing queries and user-generated requests. While existing inference engines may apply various rules against a standardized set of data records, the BNR system will determine which rules to apply dynamically, based upon the available data and the particular request. This dynamic selection of rules will enhance the flexibility of the reasoning system while reducing the computations necessary.

The design of the entire system will use a cohesive object-oriented design and modular components. The system accesses the various data sources through data adapter modules, which transforms the information from each source or web site into a consistent data model. Similarly, developers can easily add new publishing and reporting modules as well, to include publishing information to wikis, blogs or email. Finally, the rules within the rules taxonomy can be altered without affecting the design of the system, allowing an analyst to apply different rule sets to a task. This approach blends the concepts of object-oriented design with new semantic resource-driven architectures.4, 12

The high-level architecture design, shown in Figure 2, incorporates the modular approach to software design. Each of the various modules will use interfaces to communicate, increasing the flexibility of the system.

Figure 2: High-Level Architectural Diagram of the BNR System, showing different architectural components and process flow. The modular architecture reduces interdependencies, making the system flexible and adaptable.

During our Phase I SBIR project, we will determine system (functional and technical) requirements and configuration, assess design and development feasibility, and plan for Phase II development. ACME DYNAMITE COMPANY has identified the technical objectives for Phase I to provide the government with a complete assessment of the potential utility of the Behavioral Network Reasoning System. The system will meet, at a minimum, the following functional and technical requirements:

ACME DYNAMITE COMPANY will augment the above functional requirements based upon specific information that is available following contract award.

ACME DYNAMITE COMPANY has developed the Phase I work plan to achieve the technical objectives listed in the previous section. The six-month work plan is designed to provide MCSC Intel with sufficient design and feasibility information to allow them to evaluate a Phase II effort. The plan also is designed to reduce schedule and technical risks. Figure 2 shows a six-month schedule for this work plan. ACME DYNAMITE COMPANY will reuse components and software already developed on earlier programs to enhance the chances for success. ACME DYNAMITE COMPANY researchers will perform all research and development at the ACME DYNAMITE COMPANY research lab in Ellicott City, Maryland. The details of each task are listed in sections below.

​Figure 2: High-level schedule for Phase I research and development tasks

(*assumes that the work would start in June 2009). Because of its approach to identifying functional requirements, Team ACME DYNAMITE COMPANY can identify the challenges and develop solutions proactively.

A detailed requirements document, drafted with careful consideration of needs of the users, forms the basis of all effective system design efforts. This document describes the “vision” of what the system is expected to do for its users, identifies the high-level use cases and specifies the functions, characteristics, limitations, and operational environment of the new system. The requirements document forms an agreement between the system developers and the ultimate users of the new system. Based on prior experience, ACME DYNAMITE COMPANY will ensure the requirements document will evolve in an iterative fashion through different phases of the project, and as users or developers identify additional needs.

ACME DYNAMITE COMPANY has extensive experience in performing knowledge acquisition with users, and developing effective requirements documents as part of critical system designs for such clients as NSA and DIA. For the BNR system, the ACME DYNAMITE COMPANY team will develop detailed functional requirements based on knowledge gained from users, use cases, and data requirements. The Subject Matter Expert, Dr. Gonzalez, will analyze and document the user and data requirements, with support from the Principal Investigator, Mr. Runner. Team ACME DYNAMITE COMPANY will develop a preliminary Process Planning Road Map, and create project-specific planning spreadsheets to define user needs, product features, process features and process control features. Team ACME DYNAMITE COMPANY will use existing use cases, data models and KA information during the requirements and analysis phase to the maximum extent possible.

Team ACME DYNAMITE COMPANY will provide the requirements documents to the Navy COTR for review. Team ACME DYNAMITE COMPANY will adopt any recommendations, and address any concerns, prior to proceeding to the next task.

The BNR system must first construct the social network from the available data. This process is largely dependent on both the format and content of data. Network data may be available as a set of simple network transactions, which would provide limited meta-information about the content of any network traffic. The data may contain more rich information, such as the content of email messages, addresses of websites, or other information.

In addition to the people in the social network, the network nodes may also include events or places. The network nodes may also include virtual information sites such as a web site, wiki page or blog, which the system can use to derive common interests or concepts for the people who participate in those social network sites.

The system would use techniques such as entity extraction or lexical scanning to identify important terms or concepts from these websites when possible.

As part of the development during this step, Team ACME DYNAMITE COMPANY will identify the relevant social factors that we will use for the development of the social network and the rules taxonomy. These factors will form the N-dimensional space of the human network. This will allow Team ACME DYNAMITE COMPANY to identify the relevant social rules in the following task.

During the development of the Phase I prototype, Team ACME DYNAMITE COMPANY will create the processes to transform the available data into a cohesive corpus of network data. This process will include the extraction of relevant social factors and terms describing the human network, as well as identifying and representing the nature and characteristics of available metrics and other relevant information. During this network extraction process, the system will identify the nodes of interest within the corpus of available data, and create the network of information that links them together. Where possible, the system will fuse information from multiple sources to enhance the information available for the network.

Part of the extraction process may include such diverse techniques as entity extraction of unstructured text, statistical analysis of metrics, and first-tier automated reasoning to enhance the individual nodes.

As part of the development process, Team ACME DYNAMITE COMPANY will investigate social networking sites, such as Facebook or MySpace, which may contain useful data. Some of these social networking sites provide interfaces to their underlying data. Where appropriate, the developers will harvest data from these social networking sites through data adapter modules. For the initial prototype, we will restrict our focus to a small set of social networking web sites.

The Subject Matter Expert, Dr. Gonzalez, with support from the principal investigator, Mr. Runner, will identify relevant behavioral rules for inclusion in the BNR system. Team ACME DYNAMITE COMPANY will base the selection of the rules upon both the desired system requirements and tasks, and the content and characteristics of the data. Team ACME DYNAMITE COMPANY will then design a schema for storing these rules into an extensible online Rule Taxonomy.

The online Rule Taxonomy will contain the various rules and algorithms that the Network Reasoning System uses to derive its information. Because of the nature of human social networks, the rule taxonomy will include a dynamic repository for rules rather than a static set of laws. In the final system, expert analysts may create or edit hypothetical rules to determine whether their rules accurately model the behavior within a social network. As the rule set grows, the hypothetical rules will grow into a sophisticated library of rules for social dynamics.

The field of behavioral science has seen significant research for deterministic dynamic systems.9 Scientists can model such systems explicitly with physical values. These systems, such as electrical circuits or other physical networks, have physical properties that a scientist can identify and quantify. However, systems cannot model the patterns of behavior of a human social network with the same determinism.

Humans have attempted to predict patterns of human behavior for ages. Even psychology experts do not understand all rules of human behavior. In addition, various factors influence human behavior, many of which are not apparent.

For example, in Dr. Riddick’s study, she discovered that online teenagers’ displays of risky behaviors may actually just be displays.6 This study showed that some teens were simply grandstanding, or may be indicating intention or considered behavior. Additionally, other researches have done much work to characterize the so- called “generational gap.” Specifically, within every large organization we may find many micro-cultures based on the workforce characteristics of the various generational groups of a blended workforce. Figure 3 below presents the workforce characteristics that lead to the establishment of micro cultures in a blended workforce.

This lack of understanding hampers any attempt to create accurate behavioral models for an automated system. However, the system should be flexible enough to allow for experimental behavioral rules. Experts should be able to create new behavioral rules based on available network metrics, and determine their effectiveness.

The rules for identifying behaviors may become quite complex. Traditional inference engines, based on rules ontologies, do not address the complexity of network data. Ontologies do not usually include temporal measures or probabilistic calculations. Therefore, representing the behavioral rules will require either a new rule language design or an extension of an existing rule language to accommodate the rule complexity.

Figure 3: Workplace Characteristics. Team ACME DYNAMITE COMPANY will explore rules within the taxonomy to detect the existence of cultures and micro cultures in large organizations.

The rules within the taxonomy will include explicit, deterministic rules. It will also include rules that include some uncertainty. This will allow for rules that may apply when the available data does not include measurable elements for a particular node. It will also enable a novel rules engine that may eventually include probabilities in its reasoning.

Prior to proceeding onto the next step, Team ACME DYNAMITE COMPANY will provide an interim review for the customer. At this meeting, ACME DYNAMITE COMPANY will report status, demonstrate any functional capabilities of the system. ACME DYNAMITE COMPANY will solicit feedback, and incorporate any comments and suggestions into the development schedule and functional requirements.

During this phase of development, Team ACME DYNAMITE COMPANY will design the automated reasoning engine, which will augment the software data model designed in section 3.2 with the behavioral rules from section 3.3. Team ACME DYNAMITE COMPANY will base the design and development of this reasoning engine on its flexible reasoning framework used for the VULCAN program for DIA, described in section 4.2, and current state-of-the-art software libraries that offer rules inference engines, such as Jena. The reasoner will function in both an ‘on-demand’ mode for direct user requests, and an automated mode for background processing.

The reasoner will use a multi-step process. The first step of the reasoning process will select the relevant rules based upon the user’s need or the analytical task. This step will also extract the relevant data from the available sources of information. Since an unbounded social network could conceivably include everyone on the earth, part of this step will be to scope the data used in the reasoning process.

The second step of the reasoning process will identify structural network information. Structural network information, such as betweenness and closeness, may dictate some attributes, and identify certain behaviors. For instance, someone acting as a liaison between two groups of people might appear as the only link between the two clusters in a network diagram.

During the third step, the reasoning engine will apply the rules directly to the data, augmenting the information for each person, event, location, or web site. The reasoning engine will iterate through the selected rules, possibly performing multiple passes over the data with the available reasoning tools as the reasoner infers additional traits about each component in the social network.

The reasoning engine will include a temporal analysis component, which will enable the BNR system to deduce additional behaviors or information based upon trend analysis or other statistical methods. For instance, a transition of power within an organization might appear as one person replacing another over small period; figure 4 illustrates this type of transition. The temporal component, coupled with other behavioral rules, will also enable the reasoning system to predict the effects of external stimuli on a social network.

Figure 4: Display of Frequency Metrics, illustrating a significant change within the social network. The reasoning engine may identify similar changes, and apply behavioral rules to determine causes or other factors.

ACME DYNAMITE COMPANY has designed the BNR system as a web service. As part of the design of the BNR system, ACME DYNAMITE COMPANY will evaluate various designs for web services. During development, ACME DYNAMITE COMPANY will explore the most effective designs for a web service architecture. ACME DYNAMITE COMPANY developers will identify and design the necessary web service interfaces to the reasoning engine, and create a reference implementation of web services.

To validate the design of the web services interface, ACME DYNAMITE COMPANY will also provide a lightweight web-based user interface to allow the analysts to specify particular attributes of interest. This would then direct the Network Reasoning System to perform its reasoning process with the relevant subset of rules, and selectively retrieve the relevant data for the analysis.

ACME DYNAMITE COMPANY will use robust open-source implementations of web services providers, such as those available from the Apache Foundation, for its web services implementations. ACME DYNAMITE COMPANY will adhere to the recommended design patterns for web services where appropriate.

Once the behavioral information is calculated, the system must provide the derived information to the analysts. The proposed system will accomplish this by augmenting the network data with the derived behavioral attributes, and publish the results.

The BNR system will include several different publishing and representation options. Modules for each representation will be available as options, selected by either a user’s preference or the reasoning engine. For instance, the system may produce a GraphML representation of the network for use in a commercial network visualization tool.5 It may also publish or augment information in prose form, such as a wiki page or email notification.

Figure 5: A sample social network display, showing several subgroups within an organization. This visual display, based upon the Prefuse visualization toolkit, can display social graphs from the GraphML standard

As part of the initial prototype, this proposal includes a simple, lightweight network visualization utility based upon Prefuse, a robust open-source networking software package.10 This visualization will allow both developers and analysts to verify the results of the BNR system easily. The visualization utility will consume a GraphML representation, and render the results in an interactive display within a web browser.

ACME DYNAMITE COMPANY evaluates several components during its feasibility analysis. These include the following evaluations:

Team ACME DYNAMITE COMPANY is confident that we can deliver a working prototype of a Behavioral Network Reasoning system, demonstrate its capabilities, and earn user acceptance in preparation for further work in Phase II. We will investigate the feasibility of our automated reasoner design that will augment the available human social network data with additional information. We will evaluate the expected system performance using data sets with known ground truth. We will assess the accuracy of any derived information against the ground truth. We will also evaluate the performance characteristics when processing the rules and data, and assess how to maintain an acceptable performance when processing larger data sets or when using more extensive rules taxonomies.

We evaluate the development risk by evaluating the maturity of the technology as well as the complexity of the system development. We will identify and evaluate the new software designs and components that ACME DYNAMITE COMPANY incorporates into the BNR system, and assess their maintainability.

ACME DYNAMITE COMPANY will evaluate user acceptability by judging how well the prototype supports the needs of the user, and how well the system addresses all user requirements. We will also evaluate how easy the users learn the system. We will integrate or address any comments we receive during user evaluation.

ACME DYNAMITE COMPANY will evaluate the extensibility based upon how well the design addresses Phase II requirements. We will also evaluate the difficulty of adapting or generalizing the system to other tasks, rule taxonomies, bodies of data, or end users. This evaluation will identify the feasibility of the system design for eventual commercialization.

Each of the metrics will provide input into the overall feasibility score. The system design configuration that is determined to be the most feasible will be further developed, and form the basis of the phase II proposal. In case of equivalent scores, ACME DYNAMITE COMPANY will both solicit the COTR's input and consider our team's strongest capabilities in choosing the design configuration to recommend for Phase II development.

In addition to day-to-day informal contacts with the program monitor, ACME DYNAMITE COMPANY will submit interim technical progress reports in accordance with the negotiated delivery schedule.

ACME DYNAMITE COMPANY will prepare the comprehensive final that will document the work performed and the results obtained. This report will include an estimate of the technical feasibility for completing Phase II. The report will present conclusions and recommendations for the Behavioral Network Reasoning system. Each section of the report will correspond to the tasks listed in the work plan. ACME DYNAMITE COMPANY will draft each section as each task is completed. At the end of the project, ACME DYNAMITE COMPANY will combine the sections with our conclusions and recommendations to form the final report. We will submit a draft of the final report to the COTR three weeks before the end of Phase I, and deliver the final version of the report at the six-month mark.

For the three-month option period for this effort, ACME DYNAMITE COMPANY will solicit user feedback for recommended enhancements or additional requirements. In addition, ACME DYNAMITE COMPANY will explore and evaluate one or more of the potential capabilities listed below:

ACME DYNAMITE COMPANY will work with the Navy program manager to determine which capabilities we will develop as part of the option period. If the Navy exercises the SBIR continuation option, we will provide an additional capability demonstration at the end of the three-month option period, and add the results of these enhancement investigations to the feasibility study as a set of appendices. These activities will form the basis for prototype development in Phase II.

The principal investigator, Mr. Road Runner, designed and developed a utility for exploring a social network for the 2008 Visual Analytics Science & Technology (TREK) Challenge. As part of the 2008 Visualization Conference, the TREK Challenge provided an analytical challenge that resembled real-world problems. The ACME DYNAMITE COMPANY entry won an award for Effective Toolkit Integration.

This challenge involved a set of records of cell phone call transactions for a mythical terrorist network over a ten-day period. The challenge required analyzing the network social structure, identifying key personalities, and characterizing the changes to the social network.

To solve the challenge, the utility incorporated dynamic network visualizations, behavior metrics, geographic and temporal analysis. The utility applied metrics to identify significant changes in the structure of the social network. The network visualizations integrated well-known open-source software to render the network. The geographic and temporal analysis corroborated findings and identified factors that were not immediately apparent.

Classification: Top Secret Performance Period: July 2006-July 2009

The VULCAN program at DIA brings together information from a variety of intelligence sources, and provides a modern approach for intelligence analysis using tools and techniques such as social networking, faceted navigation, and online collaboration. The VULCAN architecture incorporates a full web-services framework, blogs, wikis, and similar concepts from the social web.

For the VULCAN program, ACME DYNAMITE COMPANY implemented a utility that constructed a social network from disparate data sources, and merged them into a cohesive design. The social network incorporated people, organizations, locations, events, and other resources, identifying associations among them. This utility interfaces with a faceted search engine, and is designed as a component of complex web service architecture. Analysts are able to dynamically discover and explore social networks through this social network visualization utility and glean additional information.

In addition, ACME DYNAMITE COMPANY has designed and implemented a complex reasoner that derives additional information about the various records in the faceted search engine. The reasoner allows domain experts to create and edit rules through a web service interface. The reasoner applies the rules both as an automated process and as part of a user-directed query. This reasoner also incorporates entity extraction utilities that identify common terms, and tags records with auxiliary information. As a result, this complex reasoner enables sophisticated reasoning and automated enrichment of the records used within the social network.

ACME DYNAMITE COMPANY also created a sophisticated, dynamic user interface following W3C standards. ACME DYNAMITE COMPANY developed this user interface using Adobe Flex, which supports most common back-ends to include PHP, ASP.NET, Java, and Adobe ColdFusion®. The dynamic user interface can also invoke web services, request XML or other data via HTTP, easily connecting applications to back-end services providing binary, high performance, HTTP-based data transport. The user interface also incorporates external COTS solutions, and is compliant with JSR-168.

Classification: Top Secret Performance Period: Sept. 2006 – Feb. 2009

ACME DYNAMITE COMPANY developed DILITHIUM in response to NSA requirements to provide a prototype for capturing, consolidating, and understanding customer needs for intelligence that are expressed informally during interactions with SIGINT customers. DILITHIUM uses interactive engagements that occur in the enterprise from which

customer needs expressions emerge and provides an enterprise-wide virtual needs knowledge base that serves as the master repository of knowledge about customer information needs. With each new spin cycle additional semi- formal/informal tools are incorporated into the program, thus providing one tool for users to obtain all information that they request regardless of where the actual data resides. To date ACME DYNAMITE COMPANY has incorporated a MySQL database, jabber client, and have parsed and ingested emails, web pages, Adobe PDF files, PowerPoint files, Excel files, and Microsoft Word documents. ACME DYNAMITE COMPANY has also integrated a GIS tool that allows users to search by selecting geographic locations from the map.

The DILITHIUM system scrapes HTML web pages and emails to extract content for processing. It also retrieves information from standard databases. DILITHIUM uses entity extraction techniques to extract content from the data sources, and then matches this content to other intelligence needs. ACME DYNAMITE COMPANY designed and developed DILITHIUM as a Service-Oriented Architecture (SOA) that uses Java/J2EE, Tomcat, WebHarvest, Apache POI, Apache SOLR, Agent Logic, and MySQL. DILITHIUM has an email service, a web scraper service, and connects to a number of legacy agency databases. ACME DYNAMITE COMPANY has also built an API and deployed it as an operational prototype.

ACME DYNAMITE COMPANY successfully adapted the user interface from the VULCAN program for use on DILITHIUM. This approach, utilizing modular software design and reusable code, resulted in substantial savings. As a result, ACME DYNAMITE COMPANY delivered more capabilities quickly. In some cases, ACME DYNAMITE COMPANY delivered capabilities a year prior to their delivery date.

Phase I will develop the detailed requirements for the BNR system based upon user experience and the results of validation testing. ACME DYNAMITE COMPANY will use the system requirements to develop candidate design configurations to analyze for feasibility. ACME DYNAMITE COMPANY will further define the most feasible and desirable design to facilitate a Phase II System Development Plan identifying resource levels and risk.

In addition, Phase I results in valuable products independent of Phase II. These include the design of the automated reasoner itself, the design and implementation of rules taxonomy for behavioral rules, and a web services implementation for interacting with the reasoning engine. Phase I products also will include a commercialization plan comprised of customer and competitive intelligence analysis, a draft Phase III marketing plan, and a section that identifies all intellectual property that may be exploited. ACME DYNAMITE COMPANY’s commercialization consultant, Eric Adolphe, of Intellectual Property Support Services, LLC, anticipates filing a patent application for the envisioned system at the conclusion of Phase I.

Phase I defines the scope and plan for Phase II, and positions ACME DYNAMITE COMPANY to augment the capabilities of the BNR system prototype rapidly and efficiently. Using a modular architectural design, the software components extend easily, allowing the developers to add additional capabilities to the system.

By separating the behavioral rules into an independent taxonomy, the system allows an expert user to enhance, refine, or create the rules within the taxonomy. Similarly, the system will already include components to access and fuse data from multiple sources and in multiple formats, so augmenting this capability is straightforward. ACME DYNAMITE COMPANY developers can easily enhance the web service components to provide additional services. Finally, the format for providing the results of the reasoning process already includes a design for multiple output formats, so developers can easily include an adapter for specific formats or output styles.

Similarly, the Phase III will continue to extend these modular capabilities. The Phase III, funded by other sources, will consist of any modifications required for a commercial product, and the marketing of the system.
​

Diverse application areas would benefit from software that provides additional information about a social network or predicts the effect of external stimuli. In addition to the obvious applications in intelligence or military operations, ACME DYNAMITE COMPANY has identified several potential areas for commercialization.

Corporations spend millions of dollars annually to detect and diagnose their corporate culture. Corporate culture consists of the firm’s values, beliefs, and norms. Values are things that an organization considers most important with respect to its operations, its employees, and its customers. The importance attached to how the members of an organization or social network views its culture, as well as the assumptions members hold about the nature of external nodes can have a profound impact on how the organization operates and thus on its success.1

The envisioned BNR system can detect some of the behavioral attributes such as ascetics, reclusiveness, elusiveness, anger, resistance to change, acceptance of inequality, and other indicators that would predict individual social behavioral responses in a changing environment. Therefore, a corporation could apply the envisioned system in the context of Mergers and Acquisitions (M&A), whereby one organization merges into another.

Social networking websites like Facebook, LinkedIn, Plaxo Plus, and MySpace are increasingly popular, particularly both among teenagers and adults. With the rise in SNSs popularity and use, parents have concerns that these sites might expose teens to ill-intentioned online predators, cyberbullies and increased peer pressure. There are also fears that universities and future employers may make enrollment and future hiring decisions based upon what adolescents post online in personal profiles. The BNR system could be easily adapted to monitor a teen’s online activity and alert parents when their teen’s online activities place them in jeopardy.

The envisioned system might also be used to detect other criminal activity that can support Federal Racketeer Influenced and Corrupt Organizations (RICO) Act prosecutions and other anti-social behavior that may be evident on social networking sites.

Internet advertising efforts also would benefit greatly from the ability to characterize a social network and derive additional information. Advertisers have long sought ways to provide targeted advertising without intruding on individuals’ privacy. ACME DYNAMITE COMPANY could easily adapt the BNR system to this purpose by applying different rules taxonomies to the BNR system.

The system may also be used to identify micro cultures within a large organization to help companies identify generational gaps and develop programs for effectively managing the culture of a blended workforce.

Finally, ACME DYNAMITE COMPANY could easily adapt the BNR system to monitor the status and health of employees of any organization. By monitoring internal emails and online social activity, any company could identify at-risk individuals within an organization. When a critical employee starts to exhibit signs of dissatisfaction, the organization could proactively address any problems. ACME DYNAMITE COMPANY could market this application of the BNR system to a wide variety of companies and governmental organizations.

ACME DYNAMITE COMPANY is currently engaged on several prime contracts as well as subcontracts for the DoD and intelligence agencies in which customers have directly expressed challenges with intelligently analyzing human social networks from available intelligence data in operational systems. Based upon the technology developed in Phase I, ACME DYNAMITE COMPANY will be presenting our capabilities to existing customers and partner integrators to elicit feedback and identify further security, data, and integration requirements with existing systems. Additionally, ACME DYNAMITE COMPANY will work with interested customers to acquire letters of intent for the justification of additional SBIR funding in Phase II.

Name: Road Runner

Principal Technical Consultant, ACME DYNAMITE COMPANY

Clearance: Top Secret

Education: M.S., Computer Science, Johns-Hopkins University, 1989 B.A., Computer Science, Mathematics, Rice University, 1986 Sun Java Certified Programmer

Qualifications: Road Runner is a Senior Software Engineer at Visions Systems and Technology, Inc. He has over 22 years experience in Software Architecture, Design & Development: requirements development, preliminary and critical design documentation, coding, test plans and implementation, and team and project management. He is proficient in multiple platforms, operating systems, programming languages, and development methodologies. He has been responsible for architecting, designing, developing, engineering, testing and implementing solutions. He has developed an expertise in technical leadership, innovative development, problem solving, visualization, 3D graphics, Web Development, semantic processes, and cutting-edge technologies. He has additional extensive experience in quality assurance, CMM, systems engineering and integration, operational planning, graphical user interface (GUI) design and technical writing.

Relevant Experience 2006-current

Principal Technology Consultant, Vision Systems and Technology, Inc. – Road Runner serves as Technical
​

7.2 SUBJECT MATTER EXPERT/CONSULTANT

Name: Dr. Speedy Gonzalez

Organizational and Behavioral Analyst

Clearance: Top Secret

Education: Senior Executive Institute, Carnegie-Mellon University, Pittsburgh PA 1999 Ph. D., Behavioral Science, Nova University, Fort Lauderdale FL 1992

M.S, Human Resource Management, New School for Social Research, New York, NY 1986 B.A, Sociology/Psychology, Brooklyn College, Brooklyn NY 1981

Qualifications: Dr. Gonzalez has over 30 years of experience assessing organizational behavior and diagnosing its strengths and weaknesses to provide a soluble business reengineering process to enhance employee potential and program accountability. In this capacity, Dr. Gonzalez instills and designs cost beneficial programs that provide quality performance. Her years of experience also include individual behavioral assessments in clinical environments. She is a primary consultant in quality improvement business management, business process reengineering, and mental health. She is currently pursuing continued activity as a primary consultant in these areas.

Dr. Gonzalez will be a consultant for this Phase I SBIR. Dr. Gonzalez will serve as the subject matter expert and will perform a maximum of 25% of the work. Dr. Gonzalez’s efforts will include identifying the relevant behavioral rules for inclusion in the rules taxonomy. She will also assist in determining the accuracy of the reasoning engine, and help to develop sample scenarios and data sets. She will provide expertise in any other aspects of behavioral analysis required for this effort.

Mr. Coyote will also serve as a consultant during this Phase I SBIR. Mr. Coyote will provide guidance on developing the commercialization strategy. He will also provide advice on successfully developing systems for SBIR efforts. He will perform a maximum of 8% of the work for this SBIR.

During Phase II, we anticipate bringing additional consultants to the team. ACME DYNAMITE COMPANY has partnerships with various commercial companies and relationships with several local universities.

In order to maximize the opportunity for commercial exploitation of intellectual property resulting from the development of the BNR system for this SBIR, both ACME DYNAMITE COMPANY and Dr. Speedy Gonzalez have mutually agreed that:

This approach will enable both organizations to maximize opportunities for joint or independent fund raising for Phase III exploitation, and to each benefit mutually from the anticipated commercial success of the BNR system and its component technologies.

ACME DYNAMITE COMPANY has no prior, current or pending support for a similar proposal.

[1] J. Collins and J. Porras, “Built to Last: Successful Habits of Visionary Companies”, 2002.

[2] “Emerging Gendered Behavior on Social Network Sites: Negotiating Between the Pull of the Social and the Fear of the Stalker," International Communication Association.

© 2024 Forward Edge-AI, Inc. All rights reserved.