Socrates Deligeorges

Fusion solution for soldier wearable gunfire detection systems

Currently existing acoustic based Gunfire Detection Systems (GDS) such as soldier wearable, vehicle mounted, and fixed site devices provide enemy detection and localization capabilities to the user. However, the solution to the problem of portability versus performance tradeoff remains elusive. The Data Fusion Module (DFM), described herein, is a sensor/platform agnostic software supplemental tool that addresses this tradeoff problem by leveraging existing soldier networks to enhance GDS performance across a Tactical Combat Unit (TCU). The DFM software enhances performance by leveraging all available acoustic GDS information across the TCU synergistically to calculate highly accurate solutions more consistently than any individual GDS in the TCU. The networked sensor architecture provides additional capabilities addressing the multiple shooter/fire-fight problems in addition to sniper detection/localization. The addition of the fusion solution to the overall Size, Weight and Power & Cost (SWaP&C) is zero to negligible. At the end of the first-year effort, the DFM integrated sensor networks performance was impressive showing improvements upwards of 50% in comparison to a single sensor solution. Further improvements are expected when the networked sensor architecture created in this effort is fully exploited.

A mobile self synchronizing smart sensor array for detection and localization of impulsive threat sources

Smart sensors are becoming an integral part of the evolving technology landscape; their ability to share reduced data over networks enables live data fusion, which significantly improves sensor performance and situational awareness. A lightweight, mobile acoustic sensor network has been used as an infrastructure to layer multi-sensor fusion algorithms, for detection of impulsive events such as gunfire or explosions. The system can create actionable information within seconds, and can be used to direct assets such as unmanned aerial vehicles (UAVs) to specific coordinates, for eyes-on assessment in under a minute. The sensor array will be discussed in terms of its three primary components: the smart sensors, the synchronization network, and the fusion algorithms. Performance of the array from recent tests will be examined with respect to small arms and simulated mortar fire, and producing actionable information. In addition, test results will be discussed in context of autonomous control of UAV assets and potential applications.

Biologically Inspired Circuitry that Mimics Mammalian Hearing

We are developing low-power microcircuitry that implements classification and direction finding systems of very small size and small acoustic aperture. Our approach was inspired by the fact that small mammals are able to localize sounds despite their ears may be separated by as little as a centimeter. Gerbils, in particular are good low-frequency localizers, which is a particularly difficult task, since a wavelength at 500 Hz is on the order of two feet. Given such signals, crosscorrelation- based methods to determine direction fail badly in the presence of a small amount of noise, e.g. wind noise and noise clutter common to almost any realistic environment. Circuits are being developed using both analog and digital techniques, each of which process signals in fundamentally the same way the peripheral auditory system of mammals processes sound. A filter bank represents filtering done by the cochlea. The auditory nerve is implemented using a combination of an envelope detector, an automatic gain stage, and a unique one-bit A/D, which creates what amounts to a neural impulse. These impulses are used to extract pitch characteristics, which we use to classify sounds such as vehicles, small and large weaponry from AK-47s to 155mm cannon, including mortar launches and impacts. In addition to the pitchograms, we also use neural nets for classification.

An Analog VLSI Implementation of the Inner Hair Cell and Auditory Nerve Using a Dual AGC Model

An analog inner hair cell and auditory nerve circuit using a dual AGC model has been implemented using 0.35 micron mixed-signal technology. A fully-differential current-mode architecture is used and the ability to correct channel mismatch is evaluated with matched layouts as well as with digital current tuning. The Meddis test paradigm is used to examine the analog implementations auditory processing capabilities and investigate the circuits ability to correct DC mismatch. The correction techniques used demonstrate the analog inner hair cell and auditory nerve circuits potential use in low-power, multiple-sensor analog biomimetic systems with highly reproducible signal processing blocks on a single massively parallel integrated circuit.

Biomimetic smart sensors for autonomous robotic behavior I: acoustic processing

Robotics are rapidly becoming an integral tool on the battlefield and in homeland security, replacing humans in hazardous conditions. To enhance the effectiveness of robotic assets and their interaction with human operators, smart sensors are required to give more autonomous function to robotic platforms. Biologically inspired sensors are an essential part of this development of autonomous behavior and can increase both capability and performance of robotic systems. Smart, biologically inspired acoustic sensors have the potential to extend autonomous capabilities of robotic platforms to include sniper detection, vehicle tracking, personnel detection, and general acoustic monitoring. The key to enabling these capabilities is biomimetic acoustic processing using a time domain processing method based on the neural structures of the mammalian auditory system. These biologically inspired algorithms replicate the extremely adaptive processing of the auditory system yielding high sensitivity over broad dynamic range. The algorithms provide tremendous robustness in noisy and echoic spaces; properties necessary for autonomous function in real world acoustic environments. These biomimetic acoustic algorithms also provide highly accurate localization of both persistent and transient sounds over a wide frequency range, using baselines on the order of only inches. A specialized smart sensor has been developed to interface with an iRobot Packbot® platform specifically to enhance its autonomous behaviors in response to personnel and gunfire. The low power, highly parallel biomimetic processor, in conjunction with a biomimetic vestibular system (discussed in the companion paper), has shown the systems autonomous response to gunfire in complicated acoustic environments to be highly effective.

A biomimetic robotic system for localizing gunfire

Using a biomimetic approach, a new method of acoustic signal processing was created which has tremendous advantages in complex acoustic environments. The biomimetic approach was used as the basis for a system to localize and identify sound sources in noisy and reverberant conditions. The algorithms are based on mammalian hearing and mimic the acoustic processing of the auditory periphery and midbrain. The system uses spectro‐temporal cues exploited by the auditory system including such features as interaural time difference (ITD), interaural level difference (ILD), spectral profile, and periodicity content. The initial system of algorithms were designed and tested using the EARLAB [earlab.bu.edu] software modeling environment. The system of algorithms was then adapted to a mixed‐signal real‐time hardware solution and mounted on an iRobot PackBot robotic platform to perform simple behavioral tasks. The integrated system can detect and localize gunfire in a complex, reverberant acoustic environment and orie...

A model for periodicity coding in the auditory system

The processing of complex sounds is thought to require the analysis of both spectral and temporal features. The initial processing of temporal features is believed to take place in a monaural pathway or pathways from the cochlea to the inferior colliculus (IC). We hypothesize that temporal processing begins with enhancement of temporal features by the cochlea and by cells in the cochlear nucleus and ends with a coincidence detection mechanism in the IC.

Hostile fire detection using a bio-inspired mobile acoustic sensor network

Hostile Fire Detection (HFD) sensors play an increasing role in combating asymmetric threats in both military and civilian operations. Bio-inspired advances in acoustic sensor technology have enabled small aperture arrays to localize and identify target sounds on baselines as small as 7.5 cm, making them practical for body worn and mobile applications such as UAVs. The unique approach to acoustic processing reduces acoustic information through a neural transform to key features that allow segregation of multiple targets using spectro-temporal cues creating auditory objects. The sparse representation of targets as auditory objects enables fast computationally efficient localization, identification, and tracking of several acoustic targets nearly simultaneously. The sparse representation is also ideal for information fusion among sensors over limited bandwidth networks for enhanced performance in challenging environments. Through a collaborative effort between Army research groups, the University of Califor...

A biomimetic acoustic system for threat detection and localization.

As part of our development efforts to transition cutting edge algorithms to practical devices for use in the field, hardware and software systems using the biomimetic approach are being designed for real world battlefield conditions. A new digital system has been developed that not only improves on existing sniper detection and localization technology but also enables many other capabilities useful for enhanced situational awareness. Capabilities include detection of vehicles and personnel sounds such as speech and footsteps. Systems in development include soldier‐worn, vehicle‐mounted, and robot‐mounted systems, as well as unattended ground sensor systems. Our systems can integrate acoustic target data with GPS and other sensor information using simple GUIs. These systems are modular with multiple interface ports for USB, Ethernet, RS‐232, and standard audio jacks. As these systems are transitioned to dismounted soldiers, power, weight, and size become the driving factors in design choices. Additional ca...