A Powerful Equalizer Based on Modified SVM Classifier Without Nonlinear Kernel Enabled 100-Gb/s NG-EPON System With 10-G Class

Bi, Meihua; Yu, Jiasheng; Miao, Xin; Huang, Tiancheng; Li, Longsheng; Chi, Hao; Hu, Weisheng

doi:10.1109/access.2019.2919344

Cited by 11 publications

(3 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Recently, machine learning (ML)-based equalization techniques, e.g. artificial neural network (ANN) [88]- [92] and support vector machine (SVM) [93], [94] are also proposed and investigated for short-reach IM/DD systems. These advanced equalizers have demonstrated improved performance compared with the conventional FFE/DFE equalizers.…”

Section: (A)mentioning

confidence: 99%

200 Gbps/Lane IM/DD Technologies for Short Reach Optical Interconnects

Pang

Jacobsen

et al. 2020

J. Lightwave Technol.

Self Cite

144

View full text Add to dashboard Cite

Client-side optics are facing an ever-increasing upgrading pace, driven by upcoming 5G related services and datacenter applications. The demand for a single lane data rate is soon approaching 200 Gbps. To meet such high-speed requirement, all segments of traditional intensity modulation direct detection (IM/DD) technologies are being challenged. The characteristics of electrical and optoelectronic components, and the performance of modulation, coding and digital signal processing (DSP) techniques are being stretched to their limits. In this context, we witnessed technological breakthroughs in several aspects, including development of broadband devices, novel modulation formats and coding, and high-performance DSP algorithms for the past few years. A great momentum has been accumulated to overcome the aforementioned challenges. In this paper, we focus on IM/DD transmissions, and provide an overview of recent research and development efforts on key enabling technologies for 200 Gbps per lane and beyond. Our recent demonstrations of 200 Gbps short-reach transmissions with 4level pulse amplitude modulation (PAM) and discrete multitone signals are also presented as examples to show the system requirements in terms of device characteristics and DSP performance. Apart from digital coherent technologies and advanced direct detection systems, such as Stokes-vector and Kramers-Kronig schemes, we expect high-speed IM/DD systems will remain advantageous in terms of system cost, power consumption and footprint for short reach applications in the short-to mid-term perspective.

show abstract

Section: (A)mentioning

confidence: 99%

200 Gbps/Lane IM/DD Technologies for Short Reach Optical Interconnects

Pang

Jacobsen

et al. 2020

J. Lightwave Technol.

Self Cite

144

View full text Add to dashboard Cite

show abstract

“…The reverse problem of the original problem can be obtained by finding partial derivatives of ω and b, and making them equal to zero [22]. The antithetical problem can be written as,…”

Section: Realization Of Reducing Coupling Error a Cost-sensitivmentioning

confidence: 99%

Research on Detection Method of Small Size Weld Bead Defects Based on Reluctance Measurement

Wang

2019

IEEE Access

View full text Add to dashboard Cite

To achieve non-destructive testing for small size weld beads of metal workpieces, we developed a new testing method of closed magnetic circuit reluctance measurement. According to the shape and volume of the small size weld defects of the metal workpiece, a reluctance detection model was established in the detection environment of alternating magnetic field. The relationship between different weld defects and closed magnetic circuit reluctance was quantitatively analyzed to achieve the identification of weld defects. A particle swarm optimization algorithm (PSO) was applied to optimize the cost-sensitive support vector machine (CS-SVM), which effectively reduced the coupling errors caused by the limitation of the workpiece coupling size. This new method was used to verify the weld bead detection of representative carbide saw blades. Compared with the basic support vector machine, the improved cost-sensitive support vector machine has better performance in the classification of unbalanced samples. The experimental results showed this new method can detect the weld bead of carbide saw blade with the correct rate to 98.2%. It reduced the interference of coupling error effectively. The improved cost-sensitive support vector machine not only improved the detection accuracy, but also avoided the possibility that the defective weld workpiece samples are misclassified into qualified workpieces. This study provides a guarantee for safe production and has great significance in engineering applications. The new method provides an effective solution for the application of reluctance testing technology in small size weld bead detection. INDEX TERMS Closed magnetic circuit, cost-sensitive support vector machine, coupling error, particle swarm optimization, reluctance measurement, small size weld bead.

show abstract

“…Neural network-based approaches are used by some prior works [14], [15], [16], [9] for channels equalization. Some uncommonly used low-speed equalization technologies such as Support Vector Machine based equalizer [17], [18], Fuzzy based networks equalizer [19] were more difficult for hardware implementation and are not elaborated in detail here.…”

Section: Introductionmentioning

confidence: 99%

Long Short-Term Memory Neural Equalizer

Wang

et al. 2022

SSRN Journal

View full text Add to dashboard Cite

A trainable neural equalizer based on Long Short-Term Memory (LSTM) neural network architecture is proposed in this paper to recover the channel output signal. The current widely used solution for the transmission line signal recovering is generally realized through DFE or FFE-DFE combination. The novel learning-based equalizer is suitable for highly non-linear signal restoration thanks to its recurrent design. The effectiveness of the LSTM equalizer is shown through an ADS simulation channel signal equalization task including a quantitative and qualitative comparison with an FFE-DFE combination. The LSTM neural network shows good equalization results compared to that of the FFE-DFE combination. The advantage of a trainable LSTM equalizer lies in its ability to learn its parameters in a flexible manner, to tackle complex scenario without any hardware modification. This can reduce the equalizer implantation cost for variant transmission channels and bring additional portability in practical applications.

show abstract

A Powerful Equalizer Based on Modified SVM Classifier Without Nonlinear Kernel Enabled 100-Gb/s NG-EPON System With 10-G Class

Cited by 11 publications

References 25 publications

200 Gbps/Lane IM/DD Technologies for Short Reach Optical Interconnects

200 Gbps/Lane IM/DD Technologies for Short Reach Optical Interconnects

Research on Detection Method of Small Size Weld Bead Defects Based on Reluctance Measurement

Long Short-Term Memory Neural Equalizer

Contact Info

Product

Resources

About