An official website of the United States government
With the prevalence of smartphones, pedestrians and joggers today often walk or run while listening to music. Since they are deprived of their auditory senses that would have provided important cues to dangers, they are at a much greater risk of being hit by cars or other vehicles. In this paper, we build a wearable system that uses multi-channel audio sensors embedded in a headset to help detect and locate cars from their honks, engine and tire noises, and warn pedestrians of imminent dangers of approaching cars. We demonstrate that using a segmented architecture consisting of headset-mounted audio sensors, a front-end hardware platform that performs signal processing and feature extraction, and machine learning based classification on a smartphone, we are able to provide early danger detection in real-time, from up to 60m away, and alert the user with low latency and high accuracy. To further reduce power consumption of the battery-powered wearable headset, we implement a custom-designed integrated circuit that is able to compute delays between multiple channels of audio with nW power consumption. A regression-based method for sound source localization, AvPR, is proposed and used in combination with the IC to improve the granularity and robustness of localization.
more »
« less
Demo Abstract: An Ultra-Low-Power Custom Integrated Circuit based Sound-Source Localization System
The aim of this demo is to explore the implementation of an ultra-low-power analog-to-feature ASIC to an IoT embedded system. The custom integrated circuit, designed to optimize the power consumption of a traditional sound-source localization systems, is capable of extracting the time-difference of arrival (TDoA) between 4 microphones consuming only 78.2nW. An end-to-end embedded system is presented; a microphone array is connected to the ASIC that converts the TDoA to digital information and sends it to a host computer. A machine-learning algorithm, running in the host, is then used to detect the bearing of the sound-source. During the demonstration, the audience is able to verify the benefits and drawbacks of the custom integrated circuit solution, both in the perspective of the signal-processing performance of the ASIC, and the impact it introduces to the complexity of the system’s integration.
more »
« less
- Award ID(s):
- 1704899
- PAR ID:
- 10057091
- Date Published:
- Journal Name:
- IEEE/ACM International Conference on Internet-of-Things Design and Implementation
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
This work presents a fully integrated neural interface system in a small form factor (1.9 g), consisting of a μLED silicon optoelectrode (12 μLEDs and 32 recording sites in a 4-shank configuration), an Intan 32-channel recording chip, and a custom optical stimulation chip for controlling 12 μLEDs. High-resolution optical stimulation with approximately 68.5 nW radiant flux resolution is achieved by a custom LED driver ASIC, which enables individual control of up to 48 channels with a current precision of 1 μA, a maximum current of 1.024 mA, and an update rate of > 10 kHz. Recording is performed by an off-the-shelf 32- channel digitizing front-end ASIC from Intan®. Two compact custom interface PCBs were designed to link the headstage with a PC. The prototype system demonstrates precise current generation, sufficient optical radiant flux generation (𝚽𝒆 > 𝟎. 𝟏𝟔 𝛍𝐖), and fast turn-on of μLEDs (𝒕𝒓𝒊𝒔𝒆 < 𝟏𝟎 𝛍𝐬). Single animal in vivo experiments validated the headstage’s capability to precisely modulate single neuronal activity and independently modulate activities of separate neuronal populations near neighboring optoelectrode shanks.more » « less
-
Abstract The high-luminosity upgrade of the LHC brings unprecedented requirements for real-time and precision bunch-by-bunch online luminosity measurement and beam-induced background monitoring. A key component of the CMS Beam Radiation, Instrumentation and Luminosity system is a stand-alone luminometer, the Fast Beam Condition Monitor (FBCM), which is fully independent from the CMS central trigger and data acquisition services and able to operate at all times with a triggerless readout. FBCM utilizes a dedicated front-end application-specific integrated circuit (ASIC) to amplify the signals from CO2-cooled silicon-pad sensors with a timing resolution of a few nanoseconds, which enables the measurement of the beam-induced background. FBCM uses a modular design with two half-disks of twelve modules at each end of CMS, with four service modules placed close to the outer edge to reduce radiation-induced aging. The electronics system design adapts several components from the CMS Tracker for power, control and read-out functionalities. The dedicated FBCM23 ASIC contains six channels and adjustable shaping time to optimize the noise with regards to sensor leakage current. Each ASIC channel outputs a single binary high-speed asynchronous signal carrying time-of-arrival and time-over-threshold information. The chip output signal is digitized,encoded, and sent via a radiation-hard gigabit transceiverand an optical link to the back-end electronics for analysis. This paper reports on the updated design of the FBCM detector and the ongoing testing program.more » « less
-
Approximate computing is a promising way to improve the power efficiency of deep learning. While recent work proposes new arithmetic circuits (adders and multipliers) that consume substantially less power at the cost of computation errors, these approximate circuits decrease the end-to-end accuracy of common models. We present AutoApprox, a framework to automatically generate approximate low-power deep learning accelerators without any accuracy loss. AutoApprox generates a wide range of approximate ASIC accelerators with a TPUv3 systolic-array template. AutoApprox uses a learned router to assign each DNN layer to an approximate systolic array from a bank of arrays with varying approximation levels. By tailoring this routing for a specific neural network architecture, we discover circuit designs without the accuracy penalty from prior methods. Moreover, AutoApprox optimizes for the end-to-end performance, power and area of the the whole chip and PE mapping rather than simply measuring the performance of the arithmetic units in iso-lation. To our knowledge, our work is the first to demonstrate the effectiveness of custom-tailored approximate circuits in delivering significant chip-level energy savings with zero accuracy loss on a large-scale dataset such as ImageNet. AutoApprox synthesizes a novel approximate accelerator based on the TPU that reduces end-to-end power consumption by 3.2% and area by 5.2% at a sub-10nm process with no degradation in ImageNet validation top-1 and top-5 accuracy.more » « less
-
SALT, a new dedicated readout Application Specific Integrated Circuit (ASIC) for the Upstream Tracker, a new silicon detector in the Large Hadron Collider beauty (LHCb) experiment, has been designed and developed. It is a 128-channel chip using an innovative architecture comprising a low-power analogue front-end with fast pulse shaping and a 40 MSps 6-bit Analog-to-Digital Converter (ADC) in each channel, followed by a Digital Signal Processing (DSP) block performing pedestal and Mean Common Mode (MCM) subtraction and zero suppression. The prototypes of SALT were fabricated and tested, confirming the full chip functionality and fulfilling the specifications. A signal-to-noise ratio of about 20 is achieved for a silicon sensor with a 12 pF input capacitance. In this paper, the SALT architecture and measurements of the chip performance are presented.more » « less
- Free Publicly Accessible Full Text
-
Accepted Manuscript1.0
- Conference Paper:
- The DOI is not currently available.
