AIR FORCE - AFWERX
AIR FORCE19.C SMALL BUSINESS TECHNOLOGY TRANSFER (STTR)PROPOSAL PREPARATION INSTRUCTIONS The Air Force (AF) proposal submission instructions are intended to clarify the Department of Defense (DoD) instructions as they apply to AF specific requirements. Firms must ensure their proposal meets all requirements of the Broad Agency Announcement currently posted on the DoD website at the time the solicitation closes.The AF Program Manager is Mr. David Shahady. The AF SBIR/STTR Program Office can be contacted at afsbirsttr-info@us.af.mil. For general inquiries or problems with the electronic submission, contact the DoD SBIR/STTR Help Desk via email at sbirhelpdesk@u.group (9:00 a.m. to 6:00 p.m. ET, Monday through Friday). For technical questions about the topics during the pre-announcement period (23 August 2019 through 23 September 2019), contact the Topic Authors listed for each topic on the Web site. For information on obtaining answers to your technical questions during the formal announcement period (24 September 2019 through 23 October 2019), go to . Your complete proposal?must?be submitted via the submissions site at on or before the?8:00 pm ET,?23 October 2019 deadline.? General information related to the AF Small Business Program can be found at the AF Small Business website, . The site contains information related to contracting opportunities within the AF, as well as business information and upcoming outreach/conference events. Other informative sites include those for the Small Business Administration (SBA), , and the Procurement Technical Assistance Centers, . These centers provide Government contracting assistance and guidance to small businesses, generally at no cost.(Continued on next page.)CHART 1: Consolidated STTR Topic Information LINK Excel.Sheet.12 "Book1" "Sheet1!R2C1:R5C10" \a \f 4 \h \* MERGEFORMAT Applicable TopicsPhase IPhase IITechnical Volume (Vol 2)Additional Info (Vol 5)Award Amount*Technical Duration*Final Reporting PeriodTechnical Volume (Vol 2)Additional Info (Vol 5)Technical & ReportingInitial Award AmountSpecial Topics AF19C-T010Not to exceed 5 pagesAttach a pitch deck not to exceed 15 slidesNot to exceed $25,0002 months1 monthNot to exceed 15 pagesAttached a pitch deck not to exceed 15 slidesTypically 12 monthsNot to exceed $250,000All Other TopicsNot to exceed 5 pagesAttach a pitch deck not to exceed 15 slidesNot to exceed $150,0006 months3 monthsNot to exceed 15 pagesAttach a pitch deck not to exceed 15 slidesTypically 27 monthsNot to exceed $750,000*The technical duration and final reporting duration must be added together for the total duration of the project.AF Special Topic Information The Air Force SBIR/STTR Program office is continuing to pilot new processes via “AF Special Topics” (AF19C-T010) in order to accelerate technologies to the warfighter. The AF Special Topics are different in several ways from the standard AF SBIR/STTR proposal, award and execution. Special Topics have shortened technical durations, reduced reporting requirements, and varying award amounts compared to normal STTR Topics. There are additional unique features associated with each of the Special Topics that are listed in the sections below. Consolidated information on all STTR topics can be found Chart 1. Special Topic AF19C-T010 AF19C-T010 is sponsored by the Air Force Office of Scientific Research in partnership with the AFWERX (link in the BAA announcement) a catalyst for agile Air Force engagement across industry, academia, and non-traditional contributors to create transformative opportunities and foster an Air Force culture of innovation.For all Special Topics, the Phase I proposals shall include a technical volume (uploaded in Volume 2) that shall not exceed 5 pages and a pitch/slide deck not to exceed 15 slides (uploaded in Volume 5). The technical volume and slide deck will be reviewed holistically. It is recommended (but not required) that more detailed information is included in the technical volume and higher-level information is included in the pitch deck. The cost volume (Volume 3) for the Special Topics will cover the total effort broken down into the specified technical and reporting periods (See Chart 1 for specific times). AF Special Topics shall follow the Phase I Work Plan Outline as noted in the “Phase I Work Plan Outline” section below except that there is only one required Progress report and no requirement for a Technical review due to the short technical durations. Final reporting for Phase I awardees will take the form of a presentation (with a SF298) in accordance with the Contract.It is critical that proposers for the Special Topics are registered in the System for Award Management, , you will not be eligible for an award if not registered. Additionally, verify that you are registered to receive contracts (not just grants) and that your address matches between your proposal and SAM.The AF Special Topics call for Phase II proposals shall occur shortly after Phase I award. The AF Special Topics may use the Phase II Enhancement. Unless otherwise stated in the Special Topics paragraphs above, all other requirements as noted below apply to the AF Special Topics. If there are any questions with the AF Special Topics, please contact afsbirsttr-info@us.af.mil. PHASE I PROPOSAL SUBMISSIONRead the DoD program announcement at for program requirements. When you prepare your proposal, keep in mind that Phase I should address the feasibility of a solution to the topic. For the AF, the contract period of performance for Phase I shall be nine (9) months, and the award shall not exceed $150,000. We will accept only one Cost Volume per Topic Proposal and it must address the entire nine-month contract period of performance. The Phase I topic awardees must accomplish the majority of their primary research during the first six months of the contract with the additional three months of effort to be used for generating final reports. Each AF organization may request Phase II proposals prior to the completion of the first six months of the contract based upon an evaluation of the contractor’s technical progress and review by the AF technical point of contact utilizing the criteria in section 8.0 of the DoD announcement. The last three months of the nine-month Phase I contract will provide project continuity for all Phase II awardee (see “Phase II Proposal Submissions” below); no modification to the Phase I contract should be necessary.Limitations on Length of ProposalThe Phase I Technical Volume has a 5-page-limit (excluding the Cover Sheet, Cost Volume, Cost Volume Itemized Listing (a-j), Company Commercialization Report. The Technical Volume must be in type no smaller than 10-point on standard 8-1/2" x 11" paper with one (1) inch margins.? Only the Technical Volume and any enclosures or attachments count toward the 5-page limit.? In the interest of equity, pages in excess of the 5-page limitation will not?be considered for review or award. The documents required for upload into Volume 5 using “Other” category do not count towards the 5-page limit. NOTE: The Fraud, Waste and Abuse Certificate of Training Completion (Volume 6) is required to be completed prior to proposal submission. More information concerning this requirement is provided below under “PHASE I PROPOSAL SUBMISSION CHECKLIST”.Phase I Proposal FormatProposal Cover Sheet: If your proposal is selected for award, the technical abstract and discussion of anticipated benefits will be publicly released on the Internet. Therefore, DO NOT include proprietary information in these sections.Technical Volume: The Technical Volume should include all graphics and attachments but should not include the Cover Sheet or Company Commercialization Report as these items are completed separately. The Phase I proposals shall include a technical volume (uploaded in Volume 2) that shall not exceed 5 pages and a pitch/slide deck not to exceed 15 slides (uploaded in Volume 5). The technical volume and slide deck will be reviewed holistically and there is no set format requirements for the two documents. It is recommended (but not required) that more detailed information is included in the technical volume and higher level information is included in the pitch deck. Most proposals will be printed out on black and white printers so make sure all graphics are distinguishable in black and white. To verify that your proposal has been received, click on the “Check Upload” icon to view your proposal. Typically, your uploaded file will be virus checked and converted to a .pdf document within the hour. However, if your proposal does not appear after an hour, please contact the DoD SBIR/STTR Help Desk via email at sbirhelpdesk@u.group (9:00 am to 6:00 pm ET Monday through Friday).Key Personnel: Identify in the Technical Volume all key personnel who will be involved in this project; include information on directly related education, experience, and citizenship. A technical resume of the principal investigator, including a list of publications, if any, must be part of that information. Concise technical resumes for subcontractors and consultants, if any, are also useful. You must identify all U.S. permanent residents to be involved in the project as direct employees, subcontractors, or consultants. You must also identify all non-U.S. citizens expected to be involved in the project as direct employees, subcontractors, or consultants. For all non-U.S. citizens, in addition to technical resumes, please provide countries of origin, the type of visa or work permit under which they are performing and an explanation of their anticipated level of involvement on this project, as appropriate. You may be asked to provide additional information during negotiations in order to verify the foreign citizen’s eligibility to participate on a contract issued as a result of this announcement.Phase I Work Plan OutlineNOTE: THE AF USES THE WORK PLAN OUTLINE AS THE INITIAL DRAFT OF THE PHASE I STATEMENT OF WORK (SOW). THEREFORE, DO NOT INCLUDE PROPRIETARY INFORMATION IN THE WORK PLAN OUTLINE. TO DO SO WILL NECESSITATE A REQUEST FOR REVISION AND MAY DELAY CONTRACT AWARD.At the beginning of your proposal work plan section, include an outline of the work plan in the following format:Scope: List the major requirements and specifications of the effort.Task Outline: Provide a brief outline of the work to be accomplished over the span of the Phase I effort.Milestone ScheduleDeliverablesKickoff meeting within 30 days of contract startProgress reports (Only 1 for AF Special Topics)Technical review within 6 months(N/A to AF Special Topics)Final report with SF 298Cost VolumeCost Volume information should be provided by completing the on-line Cost Volume and including the Cost Volume Itemized Listing (a-j) specified below. The Cost Volume information must be at a level of detail that would enable Air Force personnel to determine the purpose, necessity and reasonability of each cost element. Provide sufficient information on how funds will be used if the contract is awarded. The on-line Cost Volume and Itemized Cost Volume Information will not count against the 5-page limit. The itemized listing may be placed in the “Explanatory Material” section of the on-line Cost Volume (if enough room) or may be submitted in Volume 5 under the “Other” dropdown option. (Note: Only one file can be uploaded to the DoD Submission Site). Ensure that this file includes your complete Technical Volume and the information below.a. Special Tooling and Test Equipment and Material: The inclusion of equipment and materials will be carefully reviewed relative to need and appropriateness of the work proposed. The purchase of special tooling and test equipment must, in the opinion of the Contracting Officer, be advantageous to the government and relate directly to the specific effort. They may include such items as innovative instrumentation and/or automatic test equipment.b. Direct Cost Materials: Justify costs for materials, parts, and supplies with an itemized list containing types, quantities, and price and where appropriate, purposes.c. Other Direct Costs: This category of costs includes specialized services such as machining or milling, special testing or analysis, costs incurred in obtaining temporary use of specialized equipment. Proposals which include leased hardware, must provide an adequate lease vs. purchase justification or rational.d. Direct Labor: Identify key personnel by name if possible or by labor category if specific names are not available. The number of hours, labor overhead and/or fringe benefits and actual hourly rates for each individual are also necessary. e. Travel: Travel costs must relate to the needs of the project. Break out travel cost by trip, with the number of travelers, airfare, per diem, lodging, etc. The number of trips required, as well as the destination and purpose of each trip should be reflected. Recommend budgeting at least one (1) trip to the Air Force location managing the contract. f. Cost Sharing: If proposing cost share arrangements, please note each Phase I contract total value may not exceed $150,000 total, while Phase II contracts shall have an initial Not to Exceed value of $750,000. Please note cost share contracts or portions of contracts do not allow fee. NOTE: Subcontract arrangements involving provision of Independent Research and Development (IR&D) support are prohibited in accordance with Under Secretary of Defense (USD) memorandum “Contractor Cost Share”, dated 16 May 2001, as implemented by SAF/AQ memorandum, same title, dated 11 July 2001.g. Subcontracts: Involvement of a research institution is required in the project. Involvement of other subcontractors or consultants may also be desired. Describe in detail the tasks to be performed in the Technical Volume and include information in the Cost Volume for the research institution and any other subcontractors/consultants. The proposed total of all consultant fees, facility leases or usage fees, and other subcontract or purchase agreements may not exceed 60 percent of the total contract price or cost, unless otherwise approved in writing by the Contracting Officer. The STTR offeror’s involvement must equate to not less than 40 percent of the overall effort and the research institutions must equate to not less than 30 percent.Support subcontract costs with copies of the subcontract agreements. The supporting agreement documents must adequately describe the work to be performed, i.e., Cost Volume. At a minimum, an offeror must include a Statement of Work (SOW) with a corresponding detailed cost proposal for each planned subcontract.h. Consultants: Provide a separate agreement letter for each consultant. The letter should briefly state what service or assistance will be provided, the number of hours required, and hourly rate.i. Any exceptions to the model Phase I purchase order (P.O.) found at should be discussed with the Phase I Contracting Officer during negotiations. NOTE: If no exceptions are taken to an offeror’s proposal, the Government may award a contract without discussions (except clarifications as described in FAR 15.306(a)). Therefore, the offeror’s initial proposal should contain the offeror’s best terms from a cost or price and technical standpoint. Full text for the clauses included in the P.O. may be found at . Please note, the posted P.O. template is for the Small Business Innovation Research (SBIR) Program. While P.O.s for STTR awards are very similar, if selected for award, the contract or P.O. document received by your firm may vary in format/content. If there are questions regarding the award document, contact the Phase I Contracting Officer listed on the selection notification. (See item i under the “Cost Volume” section above) The Government reserves the right to conduct discussions if the Contracting Officer later determines them to be necessary.j. DD Form 2345: For proposals submitted under export-controlled topics (either International Traffic in Arms (ITAR) or Export Administration Regulations (EAR)), a copy of the certified DD Form 2345, Militarily Critical Technical Data Agreement, or evidence of application submission must be included. The form, instructions, and FAQs may be found at the United States/Canada Joint Certification Program website, . Approval of the DD Form 2345 will be verified if proposal is chosen for award.NOTE: Restrictive notices notwithstanding, proposals may be handled for administrative purposes only, by support contractors; U.Group, Oasis Systems, Riverside Research, Peerless Technologies, Engineering Network Services, and/or Stealth Entry LLC, Infinite Management Solutions, LLC. In addition, only Government employees and technical personnel from Federally Funded Research and Development Centers (FFRDCs) MITRE and Aerospace Corporations working under contract to provide technical support to AF Life Cycle Management Center and Space and Missiles Centers may evaluate proposals. All support contractors are bound by appropriate non-disclosure agreements. If you have concerns about any of these contractors, you should contact the AF SBIR/STTR Contracting Officer, Kris Croake at kristina.croake@us.af.mil.k. The Air Force does not participate in the Discretionary Technical and Business Assistance program. Contractors should not submit proposals that include Discretionary Technical and Business Assistance.PHASE I PROPOSAL SUBMISSION CHECKLISTNOTE: If you are not registered in the System for Award Management, , you will not be eligible for an award. Additionally, verify that you are registered to receive contracts (not just grants) and that your address matches between your proposal and SAM.1) The Air Force Phase I proposal shall be a nine-month effort,and the cost shall not exceed $150,000. The Special Topic shall be a three-month effort and the cost shall not exceed $25,000. 2) The Air Force will accept only those proposals submitted electronically via the DoD SBIR Web site ().3) You must submit your Company Commercialization Report electronically via the DoD SBIR website ().It is mandatory that the complete proposal submission -- DoD Proposal Cover Sheet, Technical Volume with any appendices, Cost Volume, Itemized Cost Volume Information, Fraud, Waste and Abuse Certificate of Training Completion and the Company Commercialization Report -- be submitted electronically through the DoD SBIR website at . Each of these documents is to be submitted through the Website. Please note that the Fraud, Waste and Abuse Training shall be completed prior to submission of your proposal. This is accomplished under Volume 6 of the DoD SBIR Web site (). When the training has been completed and certified, the DoD Submission Website will indicate this in the proposal which will complete the Volume 6 requirement. If the training has not been completed, you will receive an error message. Your proposal cannot be submitted until this training has been completed. The Fraud, Waste and Abuse Certificate of Training website can be found under Section 3.6 of the DoD 19.C STTR BAA Instructions. Your complete proposal?must?be submitted via the submissions site on or before the?8:00 pm ET, 23 Oct 2019 deadline.? A hardcopy?will not?be accepted. The AF recommends that you complete your submission early, as computer traffic gets heavy near solicitation close and could slow down the system. Do not wait until the last minute. The AF will not be responsible for proposals being denied due to servers being “down” or inaccessible. Please ensure your e-mail address listed in your proposal is current and accurate. The AF is not responsible for ensuring notifications are received by firms changing mailing address/e-mail address/company points of contact after proposal submission without proper notification to the AF. Changes of this nature that occur after proposal submission or award (if selected) for Phase I and II shall be sent to the Air Force SBIR/STTR site address, afsbirsttr-info@us.af.mil.AIR FORCE PROPOSAL EVALUATIONSThe AF will utilize the Phase I proposal evaluation criteria in section 6.0 of the DoD announcement in descending order of importance with technical merit being most important, followed by the qualifications of the principal investigator (and team), and followed by Commercialization Plan. The AF will utilize Phase II evaluation criteria in section 8.0 of the DoD announcement in descending order of importance with technical merit being most important, followed by the potential for Commercialization Plan, followed by the qualifications of the principal investigator (and team).The proposer's record of commercializing its prior SBIR and STTR projects, as shown in its Company Commercialization Report, will be used as a portion of the Commercialization Plan evaluation. Only firms with four or more Phase II projects that were awarded at least two years prior to a SBIR solicitation will receive a CAI score If the "Commercialization Achievement Index (CAI)”, shown on the first page of the report, is at the 20th percentile or below, the proposer will receive no more than half of the evaluation points available under evaluation criterion (c) in Section 6 of the DoD 19.C STTR instructions. This information supersedes Paragraph 4, Section 5.4e, of the DoD 19.C STTR instructions.A Company Commercialization Report showing the proposing firm has no prior Phase II awards will not affect the firm's ability to win an award. Such a firm's proposal will be evaluated for commercial potential based on its commercialization strategy.Proposal Status and DebriefingsThe Principal Investigator (PI) and Corporate Official (CO) indicated on the Proposal Cover Sheet will be notified by e-mail regarding proposal selection or non-selection. Small businesses will receive a notification for each proposal submitted. Please read each notification carefully and note the Proposal Number and Topic Number referenced. If changes occur to the company mail or email address(es) or company points of contact after proposal submission, the information shall be provided to the AF at afsbirsttr-info@us.af.mil.As is consistent with the DoD SBIR/STTR announcement, any debriefing requests must be submitted in writing within 30 days after receipt of notification of non-selection. Written requests for debrief must be submitted via afsbirsttr.af.mil through the SBIR system. Requests for debrief should include the company name and the telephone number/e-mail address for a specific point of contract, as well as an alternate. Also include the topic number under which the proposal(s) was submitted, and the proposal number(s). Debrief requests received more than 30 days after receipt of notification of non-selection will be fulfilled at the Contracting Officers' discretion. Unsuccessful offerors are entitled to no more than one debriefing for each proposal.IMPORTANT: Proposals submitted to the AF are received and evaluated by different offices within the Air Force and handled on a Topic-by-Topic basis. Each office operates within their own schedule for proposal evaluation and selection. Updates and notification timeframes will vary by office and Topic. If your company is contacted regarding a proposal submission, it is not necessary to contact the AF to inquire about additional submissions. Additional notifications regarding your other submissions will be forthcoming.We anticipate having all the proposals evaluated and our Phase I contract decisions within approximately three months of proposal receipt. All questions concerning the status of a proposal or debriefing should be directed to the local awarding organization SBIR/STTR Program Manager. PHASE II PROPOSAL SUBMISSIONSPhase II is the demonstration of the technology found feasible in Phase I. Only Phase I awardees are eligible to submit a Phase II proposal. All Phase I awardees will be sent a notification with the Phase II proposal submittal date and a link to detailed Phase II proposal preparation instructions. If the mail or email address(es) or firm points of contact have changed since submission of the Phase I proposal, correct information shall be sent to the AF at afsbirsttr-info@us.af.mil. Phase II efforts are typically 27 months in duration (24 months technical performance, with 3 additional months for final reporting) with an initial value not to exceed $750,000. NOTE: Phase II awardees should either have or start working towards having a Defense Contract Audit Agency (DCAA) approved accounting system. It is strongly urged that an approved accounting system be in place prior to the AF Phase II award timeframe. If you have questions regarding this matter, please discuss with your Phase I Contracting Officer.All proposals must be submitted electronically at by the date indicated in the notification. The technical proposal is limited to 15 pages (unless a different number is specified in the preparation instructions). The Commercialization Report, any advocacy letters, and the additional Cost Volume itemized listing (a-j) will not count against the 15-page limitation and should be placed as the last pages of the Topic Proposal file uploaded. The Phase II proposals shall also include a pitch/slide deck not to exceed 15 slides (uploaded in Volume 5). The technical volume and slide deck will be reviewed holistically and there is no set format requirements for the two documents. It is recommended (but not required) that more detailed information is included in the technical volume and higher level information is included in the pitch deck (Note: For Phase II applications, only one file can be uploaded to the DoD submission site. Ensure this single file includes your complete Technical Volume and the additional Cost Volume information.) The preferred format for submission of proposals is Portable Document Format (.pdf). Graphics must be distinguishable in black and white. Please virus-check your submissions.AIR FORCE STTR PROGRAM MANAGEMENT IMPROVEMENTSThe Air Force reserves the right to modify the Phase II submission requirements. Should the requirements change, all Phase I awardees will be notified. The Air Force also reserves the right to change any administrative procedures at any time to improve management of the Air Force STTR Program.AIR FORCE SUBMISSION OF FINAL REPORTSAll Final Reports will be submitted to the awarding AF organization in accordance with the Contract. Companies will not submit Final Reports directly to the Defense Technical Information Center (DTIC).AIR FORCE STTR 19.C Topic IndexAF19C-T001Development of Human 3D Brain Model Incorporating MicrogliaAF19C-T002Self-Correcting Multiple Source Classification and FusionAF19C-T003Adaptable Cyber Defense for Autonomous Air OperationsAF19C-T004Transfer Learning and Deep Transfer Learning for Military ApplicationsAF19C-T005Time Resolved, Spatially Filtered Imaging System for Obscure Target DetectionAF19C-T006Dynamic Bias APD Receiver ArrayAF19C-T007Human Behavior Analytics Tool (HBAT)AF19C-T008Monitoring and Diagnosis via Machinery Vibration AuditingAF19C-T009AF19C-T010Monitoring and Diagnosis via Electrical Waveform AuditingOpen Call for Science and Technology Created by Early-Stage (e.g. University) TeamsAIR FORCE STTR 19.C Topic DescriptionsAF19C-T001TITLE: Development of Human 3D Brain Model Incorporating MicrogliaTECHNOLOGY AREA(S): BiomedicalACQUISITION PROGRAM: N/AOBJECTIVE: Develop a three dimensional brain model using human myelinated neurons, astrocytes, oligodendrocytes and microglia to study neuroinflammation and neural plasticity following exposure to key stressors found in the operational environment.DESCRIPTION: Warfighters are constantly exposed to mission and non-mission degradation activities and extreme stress situations during combat. These stress responses have the potential to decrease cognitive function along with human performance, ultimately putting the warfighter at risk during missions. Therefore, understanding the effects of these stressors at the cellular level will allow for creating knowledge on how resilient specific cell pathways are, define which molecular systems are sensitive to change, and determine the key components that could be varied to defuse stressor induced cognitive degradation. In order for these questions to be addressed at the molecular level, it is imperative to have an in vitro model that physiologically represents the human brain. This model needs to incorporate myelinated neurons, astrocytes, oligodendrocytes, and microglia.Microglia are neuro-immune cells that respond to stress and injury in the brain. However, they also play a critical role in learning. In the absence of injury or stress, microglia have been shown to be responsible for secreting mediators for synaptic plasticity, memory, and neurogenesis. Following activation from injury or stress, their role switches to produce inflammatory cytokines, which cause neurons to reduce secretions of chemicals that keep microglia in an inactivated state allowing them to assist with neural plasticity (1).With the lack of human correlation observed within animal testing along with the push to find alternatives to animal use, the biggest challenge facing in vitro biology today is choosing/developing models that realistically represent a target organ. Given that greater than 95% of therapeutic drugs for neurologic disorders appear promising in rodent studies but fail in humans due to intrinsic brain differences between the species, a reproducible model for neuroscience testing needs to be generated. Development of in vitro neural models has advanced over the last few years. Neuronal cell lines such as the rat PC-12 (2) or the human SH-SY5Y (3) have benefits such as easy growth and maintenance, however, they also bring issues such as difficult extrapolation for not being of human origin (PC-12) or for being a cancer cell line with an unstable genome (SH-SY5Y). Primary cell cultures such as the rat midbrain (4) provided a brief boon to the field but are fading due to issues of interspecies differences and low biological yield. Furthermore, available in vitro models traditionally lack the multicellular complexity that allows for enhanced structural components such as myelination along with the three dimensional architecture that are found in vivo. Some researchers have been able to develop three dimensional microtissues using induced pluripotent stem cells, but microglia are not represented in this model (5).Currently, there is not an optimal human in vitro model available to address operational environmental stressors on molecular pathways critical for cognition. A novel in vitro human brain model incorporating all the cell types that are critical in learning, memory, neural plasticity and neurogenesis is imperative for advancing cognitive science investigations to benefit warfighter performance.No government furnished materials, equipment, or facilities will be provided.PHASE I: Develop a 3D human brain model incorporating myelinated neurons, microglia, astrocytes, & oligodendrocytes. Demonstrate proper cell ratios, distribution, and functionality of each cell type. Identify neuroinflammatory responses using viruses, bacteria, or other key stressors. Identify promising technology development pathways that will allow improvements beyond the scope of the STTR effort.PHASE II: Multiple regulatory and research agencies at the government level are looking to identify benchmark in vitro cell systems to be used for toxicology and health related research. Demonstrate feasibility of testing stress induced responses using this system. Collaborate with government personnel to evaluate neural plasticity and neuroinflammation following exposure to stressors found in operational environments. Based on the results of Phase I, develop prototypes for evaluation.PHASE III DUAL USE APPLICATIONS: Develop a commercial brain model that can be used for biomedical applications, drug screening, as well as general R&D. Establish baseline genetic and epigenetic profiles for this system and each sub-cell type within the system. Non-government customers: academia/pharmacology industry.REFERENCES:1. Yirmiya, R. & Goshen, I. Immune modulation of learning, memory, neural plasticity and neurogenesis Brain, Behavior, and Immunity 2011;25:181–213.2. Bercury KK, and Macklin WB. Dynamics and mechanisms of CNS myelination. Developmental cell. 2015;32(4):447-58.3. Greene LA, and Tischler AS. Establishment of a noradrenergic clonal line of rat adrenal pheochromocytoma cells which respond to nerve growth factor. Proceedings of the National Academy of Sciences of the United States of America. 1976;73(7):2424-8.4. Constantinescu R CA, Reichmann H, Janetzky DB. . Neuropsychiatric disorders an integrative approach. . Vienna: Springer; 2007.KEYWORDS: In vitro, 3D, inflammation, brain, microglia, biomedicalAF19C-T002TITLE: Self-Correcting Multiple Source Classification and FusionTECHNOLOGY AREA(S): Space PlatformsACQUISITION PROGRAM: N/AThe technology within this topic is restricted under the International Traffic in Arms Regulation (ITAR), 22 CFR Parts 120-130, which controls the export and import of defense-related material and services, including export of sensitive technical data, or the Export Administration Regulation (EAR), 15 CFR Parts 730-774, which controls dual use items. Offerors must disclose any proposed use of foreign nationals (FNs), their country(ies) of origin, the type of visa or work permit possessed, and the statement of work (SOW) tasks intended for accomplishment by the FN(s) in accordance with section 5.4.c.(8) of the Announcement and within the AF Component-specific instructions. Offerors are advised foreign nationals proposed to perform on this topic may be restricted due to the technical data under US Export Control Laws. Please direct ITAR specific questions to the AF SBIR/STTR Contracting Officer, Ms. Michele Tritt, michele.tritt@us.af.mil.OBJECTIVE: Self-Correcting Multiple Source Classification and FusionDESCRIPTION: Recent progress in machine learning techniques allows training of high accuracy classifiers for different sensor modalities. This creates opportunities for autonomous exploitation of vast amounts of sensor data. Unfortunately, classifier accuracy decreases when the statistical characteristics of the data change due to variations in operating conditions, such as weather, sensor state, geographical location, etc. The decrease in accuracy results in higher false alarm rates and consequently decreases trust in the classifier system. This is a well-known problem in the scientific community and is currently an area of active research. In the case of multiple streams of sensor data being fused, changes in one of the streams may adversely affect the entire fusion system. To avoid this, all components of the fusion system must be able to correct for changes in the incoming data and simultaneously produce a measure of confidence (reliability) in reported results. The objective of this topic is to transfer existing state of the art methodologies and develop novel machine learning technologies that, in addition to classification and fusion, are capable of monitoring the incoming streams of data and adapt existing classifiers to changes in the input distribution. The system must adapt the classifiers without retraining them and at the same time estimate and report the level of confidence in classifier results, again based on the deviation of the incoming data from what the classifier was trained on. The ability of individual classifiers to produce a measure of confidence must positively affect the performance of an entire fusion system. Performance will be evaluated on multiple labeled datasets collected under different operating conditions. In the first phase evaluation will be done using Wide Area data collected using different Electro-Optical, Infrared, and Radar sensors. This technology has both military and commercial applications. In the commercial area, quick adaptation to changes in operating conditions is crucial to data analysis in all domains, from stock market to self-driving vehicles. In order to create commercial value, the core of this technology will be sensor-independent. However, the initial thrust of this work will focus on wide area sensor data that is of interest to the DoD. Such data includes multiple data streams originated from different sensor modalities. Access to such data will require the ability to work on SIPRNet.PHASE I: Propose novel machine learning techniques that are capable of quick adaptation to changes in domain distributions without retraining the classifiers. Conduct preliminary testing using unclassified sensor data. The evaluation dataset can be chosen at the performer’s discretion. Demonstrate domain adaptation for individual classifiers and its effect on the overall quality of fusion.PHASE II: Develop a prototype multi-source domain adaptation system incorporating the technology in phase 1 and apply it to multi-source heterogeneous forensic datasets of interest to the DoD. Demonstrate the detection and false alarm performance under various operating conditions.PHASE III DUAL USE APPLICATIONS: Integrate and deploy the prototype within ISR/IC communities. Search for commercial applications.REFERENCES:1. Sugiyama, M., Yamada, M., & du Plessis, M. C . Learning under non-stationarity: Covariate shift and class-balance change. WIREs Computational Statistics, 2013.2. K. Saenko, B. Kulis, M. Fritz and T. Darrell, "Adapting Visual Category Models to New Domains" In Proc. ECCV, September 2010, Heraklion, Greece3. Yamada, M., Suzuki, T., Kanamori, T., Hachiya, H., & Sugiyama, M. (2013). Relative density-ratio estimation for robust distribution comparison. Neural computation, 25(5), 1324-1370.4. Zheng, Yu. "Methodologies for cross-domain data fusion: An overview." IEEE transactions on big data 1.1 (2015): 16-34.KEYWORDS: Sensor Data Processing; Object Recognition; Classifiers; Domain Adaptation; Information Fusion;AF19C-T003TITLE: Adaptable Cyber Defense for Autonomous Air OperationsTECHNOLOGY AREA(S): Air PlatformACQUISITION PROGRAM: N/AThe technology within this topic is restricted under the International Traffic in Arms Regulation (ITAR), 22 CFR Parts 120-130, which controls the export and import of defense-related material and services, including export of sensitive technical data, or the Export Administration Regulation (EAR), 15 CFR Parts 730-774, which controls dual use items. Offerors must disclose any proposed use of foreign nationals (FNs), their country(ies) of origin, the type of visa or work permit possessed, and the statement of work (SOW) tasks intended for accomplishment by the FN(s) in accordance with section 5.4.c.(8) of the Announcement and within the AF Component-specific instructions. Offerors are advised foreign nationals proposed to perform on this topic may be restricted due to the technical data under US Export Control Laws. Please direct ITAR specific questions to the AF SBIR/STTR Contracting Officer, Ms. Michele Tritt, michele.tritt@us.af.mil.OBJECTIVE: Develop adaptable cyber defense capabilities to support autonomous Air Force weapon system operationsDESCRIPTION: An air platform operating in a cyber-contested environment requires the ability to rapidly adapt to unforeseen and changing circumstances during mission operations [1]. Immutable software/hardware defenses that require offline patches and upgrades to mitigate cyber threats encountered in-flight are insufficient to meet mission assurance requirements. Cyber defense mechanisms for autonomous air vehicles must be resilient and have the ability to quickly analyze large amounts of data to predict attacks, subsequently self-repair and/or self-protect targeted software and hardware, learn from on-going attacks, and adapt both the software and underlying hardware to prevent the attacks from becoming successful. Two critical limiting factors to develop an adaptable cyber defense are that most software languages used operationally are not designed to be easily changed or mutated at the binary level, and the underlying hardware on which the software executes is generally fixed or only partially reconfigurable at runtime. The implications of these limitations is that the software and hardware remain vulnerable to attack during the mission and for a period of time until which the software and hardware can be repaired or replaced.The goal of this topic is to develop adaptable cyber defense capabilities that are inherently resilient to cyber-attacks and/or can rapidly detect, respond, and adapt to malware and other threats targeting the air platform during mission operations. The threat can be a result of a remote attack or malware introduced in the software, firmware or hardware supply chain of the air platform and triggered during flight. The ultimate goal of the project is to develop an architecture whose constitutive defensive software, firmware and/or hardware components can be self-assembled or rapidly evolved based upon new and unforeseen circumstances to repair or protect critical susceptibilities in real-time, and to learn from on-going attacks to rapidly counter similar threats in the future. The primary goal of this research is to develop and/or leverage game-changing adaptable and evolvable software and hardware architectures that have the promise to deliver one or more of the above capabilities [2-3]. An incremental approach with prototypes demonstrating increasing levels of capability should be used to minimize risk. A secondary goal is to investigate emergent behavior resulting from the adaptable and evolvable nature of the hardware that may lead to unconventional hardware design approaches that have only briefly been previously explored [4].PHASE I: Develop a concept, architecture and limited-scope prototype or simulation that demonstrates the ability to provide an adaptable cyber defense capabilityPHASE II: Expand the concept into a working prototype and develop increasing levels of adaptable cyber defense capabilities, such as software and hardware self-repair. Design considerations to support legacy software should be addressed.PHASE III DUAL USE APPLICATIONS: The final product will have both commercial and military system applications. Military applications include air platforms and satellite systems. Commercial applications include self-driving cars, mobile devices, SCADA systems, and artificial intelligence applications.REFERENCES:1. Office of the Air Force Chief Scientist, “Technology Horizons: A Vision for Air Force Science and Technology 2010-2030,” Sept. 2011, . C. Ofria, C. Adami, T. C. Collier, “Design of Evolvable Computer Languages”, IEEE Transactions on Evolutionary Computation 6(4):420 - 424 · September 2002.3. Adrian Thompson, “An evolved circuit, intrinsic in silicon, entwined with physics,” Proc. 1st Conf. on Evolvable Systems (ICES96), Springer LNCS, : Adaptable Computing, Evolvable Hardware, Malware Response, Embedded System Security, Avionics Cyber SecurityAF19C-T004TITLE: Transfer Learning and Deep Transfer Learning for Military ApplicationsTECHNOLOGY AREA(S): SensorsACQUISITION PROGRAM: N/AThe technology within this topic is restricted under the International Traffic in Arms Regulation (ITAR), 22 CFR Parts 120-130, which controls the export and import of defense-related material and services, including export of sensitive technical data, or the Export Administration Regulation (EAR), 15 CFR Parts 730-774, which controls dual use items. Offerors must disclose any proposed use of foreign nationals (FNs), their country(ies) of origin, the type of visa or work permit possessed, and the statement of work (SOW) tasks intended for accomplishment by the FN(s) in accordance with section 5.4.c.(8) of the Announcement and within the AF Component-specific instructions. Offerors are advised foreign nationals proposed to perform on this topic may be restricted due to the technical data under US Export Control Laws. Please direct ITAR specific questions to the AF SBIR/STTR Contracting Officer, Ms. Michele Tritt, michele.tritt@us.af.mil.OBJECTIVE: Develop militarily relevant machine learning, to include deep learning, algorithms to transfer knowledge obtained from one labeled dataset (source) to an unlabeled (target) dataset of a possibly different domain (e.g., EO < > SAR, Satellite < > airborne < >DESCRIPTION: This research will enable us to build Aided Target Recognition (AiTR) and other algorithms for environments and targets where we currently lack data or lack labeled data. The concept is to ‘transfer’ learned classifiers from one domain or set of targets to classify different targets or the same targets but in different domains. For example learning how to classify vehicles in Radar data by leveraging what we know about classifying vehicles in EO data. Statistical learning theory has produced powerful methods for learning feature mappings that maximize classification accuracy while minimizing divergence between the source and target distributions. In transfer learning we utilize the terms ‘source’ and ‘target’ data since there are really two classification problems. One classification problem uses the source data, the data that is labeled, well-understood, and has well-understood classification performance. The other classification problem is the ‘target’ classification problem where there is a small amount of data and/or a small amount of labeled data and the idea is to learn and leverage as much as possible from the source to classify the objects in the target domain. A recent example is learning how to classify positive and negative lung cancer samples by leveraging the classification knowledge of how to classify positive and negative breast cancer samples. One approach to such a problem, is to regularize standard discriminant analysis and other manifold embedding techniques with a divergence penalty. Doing so allows us to transfer the knowledge from the source domain to the target and achieve improved classification in the new domain. One class of methods finds feature embeddings or mappings that preserve manifold structure while separating the different targets and minimizing the divergence between the target and source data. This assumes an isomorphism between the source and target classes. Other approaches try to find representations that are robust across the source and target data. Our goal is to extend those ideas to a Deep learning framework. Current approaches in deep learning do not leverage the approach described above and instead use a simpler method called fine-tuning, which does not posess a firm theoretical underpinning. Instead of employing general features from a large general dataset (like ImageNet) with fine-tuning, we plan to explicitly consider the divergence between source and target distributions when learning a classifier within a deep learning framework. Specifically, we focus on the context of applying classification knowledge learned in one source setting (labeled dataset in one modality or one set of object classes) to a new target setting (unlabeled data in new modality or new object classes). This particular transfer problem, called transductive transfer learning, applies to several relevant scenarios such as i) transferring knowledge from simulated to measured data, ii) transferring from one domain such as EO to SAR, or iii) transferring knowledge to new imaging conditions or measurement devices, to name a few examples. The machine learning and statistical learning fields have made significant progress in this research area (see Pan & Yang, 2010 for a comprehensive review). Meanwhile, the area of Deep Learning has been advancing rapidly with relatively few methods dedicated to transfer (Ganin, et al. 2016). The goal of this SBIR is to extend some of the theory of transfer learning to a deep learning framework, in ways which go beyond the typical deep learning transfer approaches which use robust features from a large general dataset, then fine tune for new datasets. Instead, the methods should develop approaches based on statistical learning theory for transfer to deep learning.PHASE I: Design and develop a proof-of-concept deep transfer learning framework. This phase should focus on theoretical development with experiments to verify the theory and performance on synthetic and measured datasets. Benchmark against existing approaches in Deep Learning and transfer learning. The research should be documented in a final report and implemented in a proof-of-concept software deliverable. Government materials, equipment, data, or facilities will not be provided in Phase I.PHASE II: Mature the algorithm for use in the real world where training data may be sparse, noisy, or imbalanced. Characterize the algorithm performance, training time and testing time according to data quality and availability. Develop benchmarks for transfer across a variety of domains and datasets. The research should be documented in a final report and implemented in a proof-of-concept software deliverable. Government data may be provided in Phase II if necessary.PHASE III DUAL USE APPLICATIONS: Transition the algorithm to one or more AF weapon systems. This will include a strategy for supporting the requisite knowledge representation approach for both source and target data in an operational setting and will specifically include addressing the dynamic nature of source/target data evolution over time. The research should be documented in a final report and implemented in a proof-of-concept software deliverable.REFERENCES:1. S. J. Pan and Q. Yang. "A Survey on Transfer Learning." IEEE Transactions on Knowledge and Data Engineering, 22.10 (2010): 1345-1359.2. Yaroslav Ganin, Evgeniya Ustinova, Hana Ajakan, Pascal Germain, Hugo Larochelle, Fran?ois Laviolette, Mario Marchand, Victor S. Lempitsky. "Domain-Adversarial Training of Neural Networks." Journal of Machine Learning Research, 17 (2016): 1-35.3. Si, Si, Dacheng Tao, and Bo Geng. "Bregman divergence-based regularization for transfer subspace learning." IEEE Transactions on Knowledge and Data Engineering, 22.7 (2010): 929-942.4. Mendoza-Schrock, Olga, Mateen M. Rizki, and Vincent J. Velten. "Manifold Transfer Subspace Learning (MTSL) for Applications in Aided Target Recognition." International Journal of Monitoring and Surveillance Technologies Research (IJMSTR), 5.3 (2017): 15-3KEYWORDS: Statistical Learning Theory, Transfer Learning, Deep Learning, Transductive Transfer Learning, Source-Target Divergence, Discriminant Analysis, Manifold Embedding, Classification, Identification.AF19C-T005TITLE: Time Resolved, Spatially Filtered Imaging System for Obscure Target DetectionTECHNOLOGY AREA(S): SensorsACQUISITION PROGRAM: N/AThe technology within this topic is restricted under the International Traffic in Arms Regulation (ITAR), 22 CFR Parts 120-130, which controls the export and import of defense-related material and services, including export of sensitive technical data, or the Export Administration Regulation (EAR), 15 CFR Parts 730-774, which controls dual use items. Offerors must disclose any proposed use of foreign nationals (FNs), their country(ies) of origin, the type of visa or work permit possessed, and the statement of work (SOW) tasks intended for accomplishment by the FN(s) in accordance with section 5.4.c.(8) of the Announcement and within the AF Component-specific instructions. Offerors are advised foreign nationals proposed to perform on this topic may be restricted due to the technical data under US Export Control Laws. Please direct ITAR specific questions to the AF SBIR/STTR Contracting Officer, Ms. Michele Tritt, michele.tritt@us.af.mil.OBJECTIVE: Design, fabricate, and test passive ultrafast photography systems with effective frame rates approaching 5 trillion frames per second for wavelengths between 200 nm – 1700 nm with at least 512x512 pixelsDESCRIPTION: Current high speed cameras are commonly used for particle tracking, crack propagation, laser imaging, and in other applications. They exist in two types: continuous image sensors and burst image sensors. Continuous image sensors for high speed photography typically employ coded aperture compression and are widely available. In this mode, the camera acquires images at is normal frame rate of 5 – 30 fps. A spatial filter with a pseudo-random area of optically blocking and transmissive regions is placed between the collection optics and camera. The spatial filter is moved at a high rate using piezo stages, for example. When a fast moving object crosses the image plane of the camera, its optical image is blurred. The oscillating spatial filter, along with image processing algorithms such as TwIST, de-blur the image. The spatial filter essentially sub-divides each frame, yielding effective frame rates up to about 1000 fps. Burst image sensors feature significantly higher effective frame rates from 10,000 fps to 20 million fps, but at the expense of field of view and acquisition time. This area has a mix of commercial and experimental systems. The best experimental burst mode imagers feature a complimentary metal-oxide semiconductor (CMOS) chips. Contrary to charge coupled devices (CCDs), each pixel in a CMOS chip has its own 10 x 8 bit memory. Combined with windowing processes and parallel readout, extremely high frame rates can be acquired, but only for about 10 ms at a time before the camera memory must be purged. Burst mode obviously presents challenges for rapidly evolving events. In windowing mode, only a portion of the sensor array is read out; this increases the frame rate, but at the expense of field of view. Windowing often reduces the sensor field of view by more than 50%. Recently, the concept of compressed ultrafast photography was introduced. It is a continuous image sensor that also uses a coded spatial filter, but the sensor is a commercially available streak camera. It utilizes the entire sensor field of view. When the camera’s entrance slit is fully opened, full images can be acquired at frame rates up to 100 billion fps. Significant image blurring results, which is minimized using a spatial filter as described above. With this technique, picosecond laser pulses could be imaged while reflecting off of mirrors and “raced” through dielectric media. Additionally, objects obscured by a trubid atmosphere could be easily discerned. This technique is currently the fastest high speed camera in the experimental literature, and it used all commercial of the shelf components. No Government furnished data, facilities or equipment will be offered.PHASE I: An analysis of alternatives, preliminary system design, and a test plan for the conceptualized system in a laboratory environment. The AoA will discuss the choice of camera, wavelength range, image de-blurring, and image processing approaches. A preliminary system design will include the layout of specific optical and hardware components and an outline of the image processing approach. No Government furnished data, facilities or equipment will be offered.PHASE II: A breadboard system prototype at technology readiness level (TRL) four and a set of images demonstrating its effectiveness at clearly imaging events faster than 20 ps. A test plan for the Phase III deliverable and a conceptualized system meeting the Phase III requirements will also be included. The system will weigh no more than 75 lbs, have a 304 mm x 381 mm x 304 mm footprint, and operate off of standard 120V or 220 V, 10 A, 60 Hz circuits. No Government furnished data, facilities or equipment will be offered.PHASE III DUAL USE APPLICATIONS: A ruggedized and flight tested system; its ability to clearly image objects in outdoor, highly turbid environments will be demonstrated. A plan for military commercialization will also be included. No Government furnished data, facilities or equipment will be offered.REFERENCES:1. J. Liang, L. Gao, P. Hai, C. Li and L. V. Wang, Encrypted Three-Dimensional Dynamic Imaging Using Snapshot Time-of-Flight Compressed Ultrafast Photography, Scientific Reports 5, 15504 (2015).2. L. Gao, J. Liang, C. Li and L. V. Wang, Single-Shot Compressed Ultrafast Photography at One Hundred Billion Frames Per Second, Nature 516, 74 (2014).3. L. Zhu, Y. Chen, J. Liang, Q. Xu, L. Gao, C. Ma and L. V. Wang, Space- and Intensity-Constrained Reconstruction for Compressed Ultrafast Photography, Optica 3, 694 (2016).KEYWORDS: ultrafast imaging, focal plane array, streak camera, image processing, spatial filtering, compressed photographyAF19C-T006TITLE: Dynamic Bias APD Receiver ArrayTECHNOLOGY AREA(S): SensorsACQUISITION PROGRAM: N/AThe technology within this topic is restricted under the International Traffic in Arms Regulation (ITAR), 22 CFR Parts 120-130, which controls the export and import of defense-related material and services, including export of sensitive technical data, or the Export Administration Regulation (EAR), 15 CFR Parts 730-774, which controls dual use items. Offerors must disclose any proposed use of foreign nationals (FNs), their country(ies) of origin, the type of visa or work permit possessed, and the statement of work (SOW) tasks intended for accomplishment by the FN(s) in accordance with section 5.4.c.(8) of the Announcement and within the AF Component-specific instructions. Offerors are advised foreign nationals proposed to perform on this topic may be restricted due to the technical data under US Export Control Laws. Please direct ITAR specific questions to the AF SBIR/STTR Contracting Officer, Ms. Michele Tritt, michele.tritt@us.af.mil.OBJECTIVE: Design, develop, demonstrate, and produce a prototype 4 x 4 avalanche photodiode focal plane array with dynamic biasing and low multiplication noise.DESCRIPTION: Low photon flux detectors are a major focus of military electro-optical systems for sensing, communications, and quantum computing. Historically, these detectors have been implemented on active systems (e.g. LADAR) in the form of linear or Geiger mode avalanche photodiode (APD) focal plane arrays (FPAs). The two APD FPA forms can be differentiated by the timing circuitry of the read-out, and the dynamic range of the signal. A Geiger mode FPA will momentarily bias the APD beyond breakdown, creating a strong response to the presence of any electron present in the multiplication region. These electrons can be generated optically (signal) or thermally (noise), but the output level is the same. Meanwhile, a linear mode FPA will maintain a time invariant gain and can produce varying output levels for any number of photons, but cannot detect single photons as easily as Geiger mode APDs. The limiting factors for linear mode detectors are the multiplication noise and dark current. Given these constraints, electro-optical system designers are forced to trade signal dynamic range and overall receiver sensitivity, even when they have knowledge of their photon flux and pulse timing. An opportunity exists to create APD arrays that have higher sensitivity for known pulse trains, which would enhance signal, reduce noise, and maintain dynamic range across 100s of signal photons.Dynamically biasing an APD below its breakdown field is a potential method to increase low-noise gain and improve detectivity. The goal of this program is (a) to explore dynamic bias APD FPA designs in Phase I, (b) to produce a photodiode array with dynamic bias in Phase II, and (c) to demonstrate an imaging array with enhanced detectivity in Phase III. The basic requirements for meeting these goals are: the detector should operate at or above 200 K; the readout should be capable of adapting to changes in the pulse train to maximize SNR at frequencies greater than 10 MHz; and the APD spectral cutoff should be 1.6 microns or greater. Preference will be given to designs that offer better noise equivalent photon values and higher signal dynamic range. No government materials, equipment, data, or facilities will be provided.PHASE I: Develop a generic model for dynamic biasing of a given APD design. Optimize performance concurrently in the APD and readout for several different pulse train examples. Demonstrate lower excess noise using dynamic bias. Provide simulation code for testing/verification.PHASE II: Demonstrate statically biased APD operation on single element devices (Gain x EQE > 100%). Demonstrate spectral cut-off wavelengths of 1.6 microns or greater. Demonstrate APD operation with dynamic bias and various pulse trains. Model and design a dynamically biased readout FPA (50 micron pitch or smaller). A proof of concept FPA is desirable, but not required.PHASE III DUAL USE APPLICATIONS: Demonstrate a 4 x 4 APD FPA, or larger, using dynamic biasing and adapting to the pulse train for maximum SNR.REFERENCES:1. Hayat, M. M. and Ramirez, D. A., Multiplication theory for dynamically biased avalanche photodiodes: new limits for gain bandwidth product. Optics Express, 2012. 20(7): p. 8024.2. Hayat, M. M., et al, Breaking the buildup-time limit of sensitivity in avalanche photodiodes by dynamic biasing. Optics Express, 2015. 23(18): p. 24035.3. Namekata, N., 1.5 GHz single-photon detection at telecommunication wavelengths using sinusoidally gated InGaAs/InP avalanche photodiode. Optics Express, 2009. 17(8): p. 6275.4. US Patent US9354113 B1. “Impact ionization devices under dynamic electric fields” The United States has certain rights, including a license to have practiced on behalf of the United States the invention. Please see USPTO Reel/Frame number 034697/0153KEYWORDS: APD, Avalanche photodiode, infrared detector, SWIR, III/V, compound semiconductor, ROIC, readout integrated circuit, dynamic bias, gain modulation, LADAR, LIDAR.AF19C-T007TITLE: Human Behavior Analytics Tool (HBAT)TECHNOLOGY AREA(S): Human SystemsACQUISITION PROGRAM: N/AThe technology within this topic is restricted under the International Traffic in Arms Regulation (ITAR), 22 CFR Parts 120-130, which controls the export and import of defense-related material and services, including export of sensitive technical data, or the Export Administration Regulation (EAR), 15 CFR Parts 730-774, which controls dual use items. Offerors must disclose any proposed use of foreign nationals (FNs), their country(ies) of origin, the type of visa or work permit possessed, and the statement of work (SOW) tasks intended for accomplishment by the FN(s) in accordance with section 5.4.c.(8) of the Announcement and within the AF Component-specific instructions. Offerors are advised foreign nationals proposed to perform on this topic may be restricted due to the technical data under US Export Control Laws. Please direct ITAR specific questions to the AF SBIR/STTR Contracting Officer, Ms. Michele Tritt, michele.tritt@us.af.mil.OBJECTIVE: To research and develop a human behavior analytics tool to algorithmically process data sets, flagging potential needs or risks that indicate wellness issues, advance agency goals, and improve performance.DESCRIPTION: Recent studies by organizations such as Facebook, Cogito, and the National Center for Veterans Studies have applied machine learning technology to predict behavioral patterns. Additionally, Florida State University has trained algorithms on data from 2 million health records and achieved suicide prediction capabilities of 80-90%. All of this represents current efforts to harness machine learning technology for the detection and prediction of at risk behaviors. This would allow potential intervention in ways that enhance protective factors and advance healthy goals.Leave use patterns have been identified as a potential indicator for wellness intervention. The application of machine learning to the expanded data fields can highlight additional correlations currently unknown. Anecdotal evidence suggests not just a correlation between leave use and wellness, but also burnout and overtime trends, retention and sick leave usage, and regular aged comp-time and credit hour usage.For Phase 2, this project intends to use personnel systems data from selected sites to provide a study set of approximately 30,000 cases. The scope of the study will extend back 10 years and will explore more than 1200 data points or features for correlations and contrasts. Personally Identifiable Information (PII) protection, DoD computer system requirements, and security constraints will be appropriately addressed throughout the project. The required disciplines for this work include but are not limited to: academic research specialties in quantitative psychology, suicidology, advanced mathematics related to deep neural network modeling, data science related to Artificial Intelligence (AI), computer programing related to AI and DoD computer systems, and cultural experts. The project will require a balanced approach in which deep neural networks are one of many applicable models under consideration. A theory driven approach shall be applied throughout the project as it relates to wellness, agency goals, and performance in order to distill from the architecture and trained weights/biases of the neural network what factors it views as highly predictive. A systems viewpoint in data reduction shall demonstrate relevant correlations between the selected dataset and the aforementioned factors. The data needs to be adequately cleaned addressing corrupt, inaccurate, sparse and rogue elements for proper analysis. In support of this effort, all applicable Configuration Management policies shall be followed including source code management - the source code shall be provided with documentation. DoD, and Air Force architectures, policies, and standards shall be followed.Throughout this project all data shall be protected and secured according to applicable laws/DoD and AF directives/policies. Remote and onsite customer support shall be provided as requested/required. The final outcome of this project shall be the development and demonstration of an algorithmic tool that processes personnel systems data bi-weekly and performs predictive correlations to identify potential needs/risk patterns. This could include issues relating to wellness, performance, or other behaviors that affect agency goals (such as, but not limited to suicidality, use of overtime, comp time, and credit hours, burnout, and retention).PHASE I: R&D solution(s) that approximates the above requirements from a publicly available dataset. A selection of personnel action markers shall be identified for algorithmic training and testing to identify wellness needs and risk patterns. Proof-of-concept prototype(s) shall be developed and demonstrated using the data selected.PHASE II: Apply a balanced approach in which deep neural networks are one of multiple models under consideration for redacted data provided from personnel systems. Personnel action markers may be provided for algorithmic training and testing. Prototype(s) shall be refined to installation-ready package and shall undergo testing to verify and validate all requirements. This process may require multiple iterations before a final design is selected.PHASE III DUAL USE APPLICATIONS: If developed technology/tool passes verification, validation, and qualification testing, then it shall proceed to transitioning and implementation.REFERENCES:1. K. Krysinska and G. Martin. “The Struggle to Prevent and Evaluate: Application of Population Attributable Risk and Preventive Fraction to Suicide Prevention Research,” Suicide and Life-Threatening Behavior, 39 (5): 548-557, 20092. Suicide and Suicidal Attempts in the United States: Costs and Policy Implications” by Donald S. Shepard PhD, Deborah Gurewich PhD, Aung K. Lwin MBBS, MS, Gerald A. Reed Jr PhD, MSW, Morton M. Silverman MD in the Journal of the American Association of3. Megan Molteni, “Artificial Intelligence is Learning To Predict and Prevent Suicide” Science (March 17, 2017).4. K. Szanto, S. Kalmar, H. Hendin, Z. Rihmer, and J.J. Mann. “A Suicide Prevention Program in a Region with a Very High Suicide Rate,” Archives of General Psychiatry, 64 (8): 914-920, 2007KEYWORDS: AI, machine learning, behavioral patterns, trained algorithms, suicide, wellnessAF19C-T008TITLE: Monitoring and Diagnosis via Machinery Vibration AuditingTECHNOLOGY AREA(S): Materials/ProcessesACQUISITION PROGRAM: N/AOBJECTIVE: Troubleshoot machine operation issues through ‘Monitoring and Diagnosis via Machinery Vibration AuditingDESCRIPTION: Machine faults can be diagnosed by the changes of the system parameters or modal parameters, such as the natural frequency, damping, stiffness, etc. Since most manufacturing process generates vibrations, vibration analysis plays a major role in detecting machinery degradation before the equipment fails and potentially damages other related equipment for the ultimate purpose of avoiding unwanted breakdowns and downtime. Vibration analysis can help increase the lifetime of equipment when degradation is detected and then dealt with at an early stage. Vibration analysis of a rotating table top model has shown that some faults might exist even though they are not visible to the naked eye. The statistical features of the vibration signals in time, frequency and time–frequency domains have different representation capabilities for fault patterns. Singularity point detection, fault feature extraction, weak signal extraction, and system identification can be implemented based on vibration signals. A sophisticated vibration-fault relation model can be developed based on the vibration feature analysis. Industry has performed extensive work on smart seismic networks and data analytics through collaboration with geophysicists from NASA, USGS, energy exploration industry and academic. Characteristics of machinery vibration signals (including amplitude, frequency, phase) can be efficiently extracted using signal decomposition methods. Industry has also developed innovative intrinsic oscillation mode analysis or signal feature extraction methods, which can directly apply to machine health monitoring and diagnosis. Advanced signal processing and machine learning methods could be explored to enhance the sensitivity, robustness, reconstruction accuracy, classification specificity, and efficiency.PHASE I: Develop statistical feature extraction methods from vibration sensor signals. Time domain measurement and the corresponding frequency domain spectrum are capable of separately describing machinery vibration in terms of time and frequency. For jointly representing vibration features, it would be required to extract time-frequency domain features for signal processing and analysis.PHASE II: Develop monitoring and diagnosis software via vibration auditing. Based on the features extracted from Phase I, focus would be channeled toward optimizing statistical features in different domains from different types of faults in different diagnostic applications. Once a relationship between vibration features and faults is built, root cause diagnosis can be discerned based upon vibration signals. Then, fault diagnosis experiments on real devices could be conducted. Thereafter, based on the vibration-fault model, typical machinery systems could be constructed to validate the proposed approach.PHASE III DUAL USE APPLICATIONS: Monitoring and diagnosis via vibration auditing would have many commercial applications. A successful system could be marketed to commercial manufacturing, aerospace industry, as well as other defense customers. Additional markets might include “oil and gas” and homeland security.REFERENCES:1. Peng, Z. K., and F. L. Chu. "Application of the wavelet transform in machine condition monitoring and fault diagnostics: a review with bibliography." Mechanical systems and signal processing 18, no. 2 (2004): 199-221.2. Yan, Ruqiang, Robert X. Gao, and Xuefeng Chen. "Wavelets for fault diagnosis of rotary machines: A review with applications." Signal processing 96 (2014): 1-15.3. Li, Chuan, René-Vinicio Sánchez, Grover Zurita, Mariela Cerrada, and Diego Cabrera. "Fault diagnosis for rotating machinery using vibration measurement deep statistical feature learning." Sensors 16, no. 6 (2016): 895.KEYWORDS: manufacturing system, monitoring and diagnosis, vibrationAF19C-T009TITLE: Monitoring and Diagnosis via Electrical Waveform AuditingTECHNOLOGY AREA(S): Materials/ProcessesACQUISITION PROGRAM: N/AOBJECTIVE: Address issues pertaining to machine health through Monitoring and Diagnosis via Electrical Waveform AuditingDESCRIPTION: Some types of machine health threats (fault or attack) may be subtle and not necessarily change the power consumption of machines, but cause distorted electrical waveforms (e.g., increased harmonics) in power networks which may affect the precision and functions of electrical machines. The attacks may be direct or indirect. In direct attacks, a malicious device may be plugged into a power outlet and inject harmonics to the power network of machines. The indirect methods may involve hacking and controlling an electrical machine in order to generate distorted electrical waveforms to affect other machines in the power network. For instance, if denial of service (DOS) occurs, the system might become unstable, resulting in unusual harmonics and torque ripples, which later affect product quality. In this task, it is proposed to analyze electrical waveform data from strategically-placed sensors in manufacturing systems for health monitoring and diagnosis. No record in industry suggests this approach has not been attempted before. To achieve this goal, a high dimensional analysis method and information incorporation mode would need to be developed. Traditional time series analysis or machine learning methods ignore some unique characteristics of the multi-stream measurement data; in particular, the coexistence of strong temporal correlation and inter-stream relatedness is not accounted for. The machine learning formulation proposed in this task for multiple time series is intuitively nonparametric regression in statistical learning theory, which uses multiple coevolving time series data to capture both the temporal dependence and inter-series relatedness.PHASE I: Build the relationship model between system statistics (e.g. “normal state, controller attack, attack, DOS attack, short circuit fault,” etc.) and electrical waveform data (e.g, total harmonic distortion, current ripples, voltage/current unbalance, etc.). Firstly, validation that electrical waveform of manufacturing systems can be used to detect cyber and physical attacks would need to take place. Then, a disaggregation model to map the relationship to assist root cause diagnosis could be developed.PHASE II: Develop monitoring and diagnosis software to classify the observed data into “trend” functions and anomalies based on the “normal” behavior data and simulated “faulty” data. Once the trend and fault libraries are built, the monitoring system detects anomalies when the fitting error is larger than the threshold. Then a classification model can be learned to classify the threat source to the most possible location.PHASE III DUAL USE APPLICATIONS: Monitoring and diagnosis via electrical waveform have many commercial applications. A successful system could be marketed to commercial manufacturing, aerospace industry as well as other defense customers. Additional markets might include the smart home, construction, and power industries.REFERENCES:1. F. Li, B. Yang, J. Ye, and W. Song, “Generator fault diagnosis based on sparsely placed sensors in power networks,” Sensors, 2019, submitted.2. B. Yang, F. Li, J. Ye, and W. Song, Condition Monitoring and Fault Diagnosis of Generators in Power Networks Conference IEEE Power & Energy Society General Meeting, 2019.3. J. Guo, J. Ye, and A. Emadi, “DC-Link current and voltage ripple analysis considering anti-parallel diode reverse recovery in voltage source inverters,” IEEE Transactions on Power Electronics, vol. 33, no. 6, pp. 5171-5180, June 2018.4. F. Peng, J. Ye, A. Emadi, and Y. Huang, “Position sensorless control of switched reluctance motor drives based on numerical method,” IEEE Transactions on Industry Applications, vol. 53, no.3, pp. 2159-2168, May-June 2017.KEYWORDS: manufacturing system, monitoring and diagnosis, electrical waveformAF19C-T010 TITLE: Open Call for Science and Technology Created by Early-Stage (e.g. University) TeamsTECHNOLOGY AREA(S): Multiple Topics. Special emphasis on Quantum ScienceOBJECTIVE: This is an AF Special Topic partnership between AFOSR and AFWERX, please see the above AF Special Topic instructions for further details. A Phase I award will be completed over 3 months with a maximum award of $25K and a Phase II may be awarded for a maximum period of 12 months and $200K. The objective of this topic is to provide an established accelerated technology transition pathway for promising science and technology under development by university teams (undergraduate, graduate, doctorate, post-doctorate, faculty/staff). This includes, but is not limited to, those that have participated in a government sponsored innovation event such as: I-Corp teams, Defense Enterprise Science Initiative, AFRL University Challenge, Hacking For Defense, Hack-A-Thon, etc. This topic is intentionally broad in scope, directed at disruptive innovative advancements that may not be covered by any other specific STTR topic, and designed to explore options for supplementing and expanding public/private partnerships capability with the Air Force Office of Scientific Research. The goal is to stimulate science and technology innovation, foster greatly accelerated technology transfer thru cooperative R&D, and increase private sector commercialization of innovations derived from federal R&D.This topic is aimed at early stage teams (e.g. university teams, research spin-offs or very early stage companies) that have an Minimum Viable Product (MVP) and have partnered with a university or non-profit organization who can help them take their prototype and turn it in to a sustainable business (e.g. university entrepreneurship centers, technology transfer offices, non-profit entrepreneurship institutions).DESCRIPTION: Academia is producing disruptive science and technology innovations at an increasingly rapid pace. Hence, rather than utilizing a pre-defined requirements approach, this topic is intended to be an open call for ideas and technologies that may not be currently listed (i.e. the unknown-unknown) under STTR topics, but nonetheless still fit within broad interest areas of the Air Force Office of Scientific Research (AFOSR). These broad areas (Engineering and Complex Systems, Information and Networks, Physical Sciences, and Chemistry/Biological Sciences) are covered in greater detail at be eligible, offeror(s) must be teams that have formed companies and partnered with a university (e.g. university entrepreneurship centers, university technology transfer offices).The offeror should demonstrate their technical capability by demonstrating a credible and high-potential minimum viable product (MVP) along with a credible plan for developing the prototype to a commercially available solution. This topic is not looking for fully formed products, and it is acceptable if the solutions are earlier stage. If the offeror has a later stage solution that already has paying customers, it may make more sense to apply to the SBIR ‘Open Innovation Topic’ AF19.2-001.The offeror should demonstrate their ability to perform the Phase I research by showing that they have an understanding of which Air Force stakeholders could make use of their solution. In general, it will be beneficial to be more specific about the stakeholder, (i.e. listing a person’s name and their exact position and organization is better than just saying ‘pilots could use this’). For early-stage (e.g. student) teams who have never learned about the Air Force and are unsure of where to start, we recommend reaching out to AFWERX ().The offeror should demonstrate their commercialization capability by demonstrating the results of the commercialization efforts of their partner university or non-profit partner (i.e. a university entrepreneurship center, tech transition office, non-profit entrepreneurship center) and showing a credible plan for turning the prototype or MVP into a sustainable business. It will also be important to show the potential for commercialization in the non-defense market (i.e. Dual-Use technologies).FOCUS AREAS: While This topic is open to all research areas and business ideas that meet the above criteria, there are some areas that are of particular interest to the Air Force right now, these can be found at . If your solution may meet one of these focus areas, please list the focus area number in your proposalThe alignment between a proposal and a Focus Area can strengthen an application. This also does not preclude companies who are looking to solve other problems that are not listed in the Focus Areas to submit to this topic, it is simply intended to give indications of areas of special focus for the Air Force at this particular point in time.PHASE I: Validate the product-market fit between the proposed solution and a potential US Air Force stakeholder and define a clear and immediately actionable plan for running a trial with the proposed solution and the proposed US Air Force customer. The period of performance for Phase I is targeted at under an academic semester (ideally 3 months or less) with monetary awards in Phase I not to exceed $25k.This feasibility study should directly address:1. Offeror(s) must focus on who the prime potential US Air Force end user(s) is and articulate how they would use your solution(s) (i.e., the one who is most likely to be an early adopter, first user, and initial transition partner).2. Deeply explore the problem or benefit area(s) which are to be addressed by the solution(s) - specifically focusing on how this solution will impact the end user of the solution.3. Define clear objectives and measurable key results for a potential trial of the proposed solution with the identified Air Force end user(s).4. Identify any additional specific stakeholders beyond the end user(s) who will be critical to the success of any potential trial. This includes, but is not limited to, program offices, contracting offices, finance offices, information security offices and environmental protection offices.5. Describe if and how the demonstration can be used by other DoD or governmental customers.6. Development of plans for MVPs, prototypes, manufacturing, distribution and scaling of the idea into an actual solution for DoD customers.7. Development of the business, including interest from non-governmental customers, potential sources of private funding, and formation of the team (to include new employees, partners, advisors and investors). The funds obligated on the resulting Phase I STTR contracts are to be used for the sole purpose of conducting a thorough feasibility study using scientific experiments, laboratory studies, commercial research and interviews. MVPs or Prototypes may be developed with STTR funds during Phase I studies to better address the risks and potential payoffs in innovative technologies. Phase I will conclude with a short report and video outbrief and/or telecon with select members of the Air Force Office of Scientific Research.PHASE II: Develop, install, integrate and demonstrate a prototype system determined to be the most feasible solution during the Phase I feasibility study. If selected, Phase II awards will be granted up to $250k and are targeted for periods of performance less than one year in duration. This demonstration should focus specifically on:1. Evaluating the proposed solution against the objectives and measurable key results as defined in the Phase I feasibility study.2. A clear transition path for the proposed solution that takes into account input from all affected stakeholders including but not limited to: end users, engineering, sustainment, contracting, finance, legal, and cyber security.3. Specific details about how the solution can integrate with other current and potential future solutions.4. How the solution can be sustainable (i.e. supportability)5. Clearly identify other specific DoD or governmental customers who want to use the solution6. Clearly identify other non-governmental customers who want to use the solution.PHASE III DEFENSE APPLICATION: The student-led team small business will pursue commercialization of the various technologies developed in Phase II for transitioning expanded mission capability to a broad range of potential government and civilian users and alternate mission applications. Direct access with end users and government customers will be provided with opportunities to receive Phase III awards for providing the government additional research & development, or direct procurement of products and services developed in coordination with the program.Lockheed Martin is interested in a possible transition of this technology. Awardees of a Phase I should contact the AF SBIR/STTR Program office at afsbirsttr-info@us.af.mil to obtain the Lockheed Martin Point of Contact for this topic.a. This SBIR is NOT awarding grants, it is awarding contracts, when registering in , be sure to select ‘YES’ to the question ‘Do you wish to bid on contracts?’ in order to be able to compete for this SBIR topic. If you are only registered to compete for grants, you will be ineligible for award under this topic. For more information please visit . We are working to move fast, please register in SAMs and if already registered please double check your CAGE codes, company name, address information, DUNS numbers, ect. , If they are not correct at time of submission, you will be ineligible for this topic. In order to ensure this, please include, in your 15-slide deck, a screenshot from as validation of your correct CAGE code, DUNS number and current business address along with the verification that you are registered to compete for All Contracts. It is the responsibility of the contractor to ensure that the data in the proposal and the data in are aligned. For more information please visit . Please note that each company may only have one active ‘Open Topic’ award at a time. If a company submits multiple technically acceptable proposals, only the proposal with the highest evaluation will be awarded. If multiple proposals are evaluated to be equal, the government will decide which proposal to award based upon the needs of the Air Force.The ‘DoD SBIR/STTR Programs Funding Agreement Certification’ form must be completed and signed at the time of *Proposal Submission* and can be found at *****Proposals submitted under this topic may relate to technologies restricted under the International Traffic in Arms Regulation (ITAR) which controls defense-related materials/services import/export, or the Export Administration Regulation (EAR) which controls dual use items. Foreign National is defined in 22 CFR 120.16 as a natural person who is neither a lawful permanent resident (8 U.S.C. § 1101(a)(20)), nor a protected individual (8 U.S.C. § 1324b(a)(3)). It also includes foreign corporations, business associations, partnerships, trusts, societies, other entities/groups not incorporated/organized to do business in the United States, international organizations, foreign governments, and their agencies/subdivisions.Offerors must identify Foreign National team members, countries of origin, visa/work permits possessed, and Work Plan tasks assigned. Additional information may be required during negotiations to verify eligibility. Even if eligible, participation may be restricted due to U.S. Export Control Laws.NOTE: Export control compliance statements are not all-inclusive and do not remove submitters’ liability to 1) comply with applicable ITAR/EAR export control restrictions or 2) inform the Government of potential export restrictions as efforts proceed.*****REFERENCES:1. FitzGerald, B., Sander, A., & Parziale, J. (2016). Future Foundry: A New Strategic Approach to Military-Technical Advantage. Retrieved June 12, 2018, from . Blank, S. (2016). The Mission Model Canvas – An Adapted Business Model Canvas for Mission-Driven Organizations. Retrieved June 12, 2018, from . US Department of Defense. (2018). 2018 National Defense Strategy of the United States Summary, 11. Retrieved from . Torrance, W. E. (2013). Entrepreneurial campuses: Action, impact, and lessons learned from the Kauffman campuses initiative. Retrieved from : Open, Other, Disruptive, Innovation, Defense Related TechnologiesPHONE/EMAIL: N/A (please reference ) ................
................
In order to avoid copyright disputes, this page is only a partial summary.
To fulfill the demand for quickly locating and searching documents.
It is intelligent file search solution for home and business.
Related download
- idiq contracts verification of adequate accounting
- b 419322 b 419322 2 nci information systems inc
- understanding the different types of dcaa audits
- defense contract audit agency grf cpa
- dcaa approved accounting system myth
- dcaa compliant accounting systems florida sbdc
- office of the senior vice president for research at penn state
- defense acquisition university
- certificate of accounting and billing system adequacy
- air force afwerx