Award Data

LongShortWay Inc. and Northeastern University propose a family of feature reduction and ensemble classifier methods based on Principal Component and Dynamic Logic feature clustering algorithms. New methods combine feature clustering with non-linear feature reduction via manifold learning, and bagging, boosting, and stacking ensemble algorithms.

In this effort, Innoveering will integrate and test a closed-loop active control system for scramjet isolator shock system positioning. The approach is to control the fuel flow to the engine to position the shock train leading edge at a specified location in the isolator. The control system includes three basic elements: a shock position sensing system based, a fast response fuel valve that adjust ...

ABSTRACT: In this effort selected SBIR technologies will be matured and merged to establish the Adaptive Cyber-secure Cross-layer Communications-Classification System (AC4S) for enhancing the throughput, spectral efficiency, speed, reliability and security performance of software defined radio (SDR) communication networks. One of the core technologies in the AC4S architecture is the Cyber Superior ...

ABSTRACT: In this effort selected SBIR technologies will be matured and merged to establish the Adaptive Cyber-secure Cross-layer Communications-Classification System (AC4S) for enhancing the throughput, spectral efficiency, speed, reliability and security performance of software defined radio (SDR) communication networks. One of the core technologies that forms the basis of AC4S is the AXL-ROSA s ...

As the carry and protective gear of the modern war fighter increases, the burden on the human body will necessarily increase. In our present TALOS MkIII project, we are developing lower body augmentation to preserve speed and agility while bearing this weight. Yet we cannot ignore the impact of this weight on the upper body: in this project we propose to develop an upper body exoskeleton with p ...

A critical aspect of exoskeleton control that has to date introduced a performance limitation is the ability of the exoskeleton to recognize the intent of the operator so it can apply assistance to their desired motion. This intent recognition effort is typically solved using ad-hoc methods where subject matter experts make design decisions and tune transitions to identify intended maneuvers as re ...

Automatic speech recognition (ASR) technology is in wide use today and has been successfully integrated into a number of applications. Although there are also many potential applications for automatic speaker identification (SID), SID accuracy rates are generally not sufficient for widespread use in practical applications. For high accuracy ASR and SID, the microphone must be located near the talk ...

Toyon Research Corp. and the Penn State Univ. propose research and development of innovative algorithms for classifying objects and activities observed in high-dimensional data extracted from multi-sensor motion imagery. The proposed algorithms include novel feature clustering techniques to enable effective characterization of intra-class and inter-class appearance variations in datasets containin ...

Experimental data from a number of DoD supported research programs have indicated that electrical systems capable of producing highly repetitive bursts of high voltage, fast risetime pulses are a critical enabling technology for applications tied to nonequilibrium physical processes, such as combustion, boundary layer flow, and the generation of high power EM waves. Recognizing the important role ...

Novel algorithms were developed for ecient multi-sensor fusion of correlated high-dimensional data to support target detection. In our compressive sensing framework, high-dimensional data is compressed using low dimensional random projection matrices. When the high-dimensional data exhibits low-dimensional structures, this scheme is capable of capturing all the significant informative with fewer r ...