Alpha–Gamma Discrimination in BaF<sub>2</sub> Using FPGA-Based Feedforward Neural Network

Yang, Chenfei; Feng, C. Q.; Dong, Wenhao; Jiang, Di; Shen, Zuojun; Liu, Shubin; An, Qi

doi:10.1109/tns.2017.2691729

Cited by 14 publications

(13 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The processed data streams are then delayed for several clock periods and finally summed together to reconstruct the corrected digital waveform. As for the design of the correction filter for this TIADC, since 40 parallel channels are needed to achieve real time processing of the 96 Gbps data stream, if we implement this parallel algorithm using the previous method based on interpolation filter [38], the signal process would be expressed as in 0,0 0,1 0,39 0 According to (11), it means that for the data stream in each channel Xi, the data need to be further fanned out to 40 streams.…”

Section: Real-time Correction Algorithm Implementationmentioning

confidence: 99%

“…As mentioned above, the most comprehensive information of the detector output signal can be obtained through waveform digitization in physics experiments. Especially in some experiments, the digitized waveform needs to be used for Pulse Shape Discrimination (PSD) [11][40]- [42]. Better performance of the TIADC would allow more precise observation of the detector output signal.…”

Section: B Simulationsmentioning

confidence: 99%

“…According to (11), it means that for the data stream in each channel Xi, the data need to be further fanned out to 40 streams.…”

Section: Real-time Correction Algorithm Implementationmentioning

confidence: 99%

“…AVEFORM digitization is a preferable solution in physics to obtain the most detailed information from the signals out of detectors, and has thus been employed in many physics experiments [1]- [11]. With the development of electronics, especially ASIC design on Analog-to-Digital Converters (ADCs), sampling speed has been increasing.…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

An 8-Gs/s 12-Bit TIADC System With Real-Time Broadband Mismatch Error Correction

Liu

Jiang

Dong

et al. 2018

IEEE Trans. Nucl. Sci.

Self Cite

View full text Add to dashboard Cite

High sampling speed can be achieved using multiple Analog-to-Digital Converters (ADCs) based on the Time-Interleaving A/D Conversion (TIADC) technique. Various types of methods were proposed to correct the mismatch errors among parallel ADC channels in TIADC systems, which would deteriorate the system performance. Traditional correction methods based on digital signal processing have good performance, however often only for input signals limited in a narrow frequency band. In this paper, we present our recent work on design of an 8-Gsps 12-bit TIADC system and implementation of real-time mismatch correction algorithms in FPGA devices, over a broad band of input signal frequencies. Tests were also conducted to evaluate the systems performance, and the results indicate that the Effective Number of Bits (ENOB) is enhanced to be better than 8.5 bits (<800 MHz) and 8 bits from 800 MHz to 1.6 GHz after correction, almost the same with that of the ADC chip employed. Index Terms-time-interleaved technique, high-speed high-resolution A/D conversion, mismatch errors, real-time correction algorithms, broad band. I. INTRODUCTION AVEFORM digitization is a preferable solution in physics to obtain the most detailed information from the signals out of detectors, and has thus been employed in many physics experiments [1]-[11]. With the development of electronics, especially ASIC design on Analog-to-Digital Converters (ADCs), sampling speed has been increasing. With the Time Interleaved A/D Conversion (TIADC) technique, the system sampling speed can be greatly enhanced beyond single ADC ASIC's capability [8]-[10], which makes the study in this direction a research hot spot.

show abstract

Section: Real-time Correction Algorithm Implementationmentioning

confidence: 99%

Section: B Simulationsmentioning

confidence: 99%

“…According to (11), it means that for the data stream in each channel Xi, the data need to be further fanned out to 40 streams.…”

Section: Real-time Correction Algorithm Implementationmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

An 8-Gs/s 12-Bit TIADC System With Real-Time Broadband Mismatch Error Correction

Liu

Jiang

Dong

et al. 2018

IEEE Trans. Nucl. Sci.

Self Cite

View full text Add to dashboard Cite

show abstract

“…Real-time state discrimination is important in applications like fast feedback control of quantum state operations. Considering that the field-programmable gate arrays (FPGA) [8] based system has the ability to process data faster [9], we implement real time state discrimination with machine learning algorithms on an embedded hardware system instead of traditional CPU/GPUs implemention [10]. We apply FPGA-based preprocessing and ARM-based feedforward neural networks for fast qubit readout.…”

Section: Introductionmentioning

confidence: 99%

Fast High-Fidelity Readout of a Single Trapped-Ion Qubit via Machine-Learning Methods

et al. 2019

View full text Add to dashboard Cite

In this work, we introduce machine learning methods to implement readout of a single qubit on 171 Yb + trapped-ion system. Different machine learning methods including convolutional neural networks and fully-connected neural networks are compared with traditional methods in the tests. The results show that machine learning methods have higher fidelity, more robust readout results in relatively short time. To obtain a 99% readout fidelity, neural networks only take half of the detection time needed by traditional threshold or maximum likelihood methods. Furthermore, we implement the machine learning algorithms on hardware-based field-programmable gate arrays and an ARM processor. An average readout fidelity of 99.5% (with 10 5 magnitude trials) within 171 µs is demonstrated on the embedded hardware system for 171 Yb + ion trap. * Program available on GitHub: https://github.com/quantumiracle/On board FNN qubit discrimination †

show abstract

Spectrometry analysis based on approximation coefficients and deep belief networks

Tang

Gong

et al. 2018

NUCL SCI TECH

View full text Add to dashboard Cite

Alpha–Gamma Discrimination in BaF₂ Using FPGA-Based Feedforward Neural Network

Cited by 14 publications

References 11 publications

An 8-Gs/s 12-Bit TIADC System With Real-Time Broadband Mismatch Error Correction

An 8-Gs/s 12-Bit TIADC System With Real-Time Broadband Mismatch Error Correction

Fast High-Fidelity Readout of a Single Trapped-Ion Qubit via Machine-Learning Methods

Spectrometry analysis based on approximation coefficients and deep belief networks

Contact Info

Product

Resources

About

Alpha–Gamma Discrimination in BaF2 Using FPGA-Based Feedforward Neural Network

Cited by 14 publications

References 11 publications

An 8-Gs/s 12-Bit TIADC System With Real-Time Broadband Mismatch Error Correction

An 8-Gs/s 12-Bit TIADC System With Real-Time Broadband Mismatch Error Correction

Fast High-Fidelity Readout of a Single Trapped-Ion Qubit via Machine-Learning Methods

Spectrometry analysis based on approximation coefficients and deep belief networks

Contact Info

Product

Resources

About

Alpha–Gamma Discrimination in BaF₂ Using FPGA-Based Feedforward Neural Network